Optimum LLM Perf Leaderboard
Hugging Face Optimum Benchmark performance leaderboard for LLM inference configurations across PyTorch CUDA, CPU, OpenVINO, ONNX Runtime, quantization schemes, and hardware profiles.
500rows
decode_throughputprimary metric
2026-05-06sampled
Metadata
Metrics
Decode Throughput, Prefill Throughput, Decode Latency P50 (lower is better), Prefill Latency P50 (lower is better), Decode Efficiency, Prefill Efficiency, Decode Max VRAM (lower is better), Prefill Max VRAM (lower is better)
| Rank | Subject | Decode Throughput | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | trl-internal-testing/tiny-random-LlamaForCausalLM on ['NVIDIA A10G'] (pytorch, unquantized) | 383.26 | — | Imported | 2026-05-06 |
| 2 | trl-internal-testing/tiny-random-LlamaForCausalLM on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 367.20 | — | Imported | 2026-05-06 |
| 3 | trl-internal-testing/tiny-random-LlamaForCausalLM on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 352.08 | — | Imported | 2026-05-06 |
| 4 | trl-internal-testing/tiny-random-LlamaForCausalLM on ['NVIDIA A10G'] (pytorch, unquantized) | 348.18 | — | Imported | 2026-05-06 |
| 5 | trl-internal-testing/tiny-random-LlamaForCausalLM on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 344.72 | — | Imported | 2026-05-06 |
| 6 | trl-internal-testing/tiny-random-LlamaForCausalLM on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 342.42 | — | Imported | 2026-05-06 |
| 7 | trl-internal-testing/tiny-random-LlamaForCausalLM on ['NVIDIA A10G'] (pytorch, unquantized) | 340.81 | — | Imported | 2026-05-06 |
| 8 | trl-internal-testing/tiny-random-LlamaForCausalLM on ['NVIDIA A10G'] (pytorch, unquantized) | 338.44 | — | Imported | 2026-05-06 |
| 9 | trl-internal-testing/tiny-random-LlamaForCausalLM on ['NVIDIA A10G'] (pytorch, unquantized) | 319.77 | — | Imported | 2026-05-06 |
| 10 | trl-internal-testing/tiny-random-LlamaForCausalLM on ['NVIDIA A10G'] (pytorch, unquantized) | 316.18 | — | Imported | 2026-05-06 |
| 11 | trl-internal-testing/tiny-random-LlamaForCausalLM on ['NVIDIA A10G'] (pytorch, unquantized) | 315.98 | — | Imported | 2026-05-06 |
| 12 | trl-internal-testing/dummy-GPT2-correct-vocab on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 312.83 | — | Imported | 2026-05-06 |
| 13 | trl-internal-testing/tiny-random-LlamaForCausalLM on ['NVIDIA A10G'] (pytorch, unquantized) | 311.61 | — | Imported | 2026-05-06 |
| 14 | trl-internal-testing/tiny-random-LlamaForCausalLM on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 309.61 | — | Imported | 2026-05-06 |
| 15 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, unquantized) | 309.53 | — | Imported | 2026-05-06 |
| 16 | trl-internal-testing/tiny-random-LlamaForCausalLM on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 309.02 | — | Imported | 2026-05-06 |
| 17 | trl-internal-testing/dummy-GPT2-correct-vocab on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 306.45 | — | Imported | 2026-05-06 |
| 18 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, unquantized) | 298.70 | — | Imported | 2026-05-06 |
| 19 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, unquantized) | 288.73 | — | Imported | 2026-05-06 |
| 20 | trl-internal-testing/dummy-GPT2-correct-vocab on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 284.94 | — | Imported | 2026-05-06 |
| 21 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, unquantized) | 281.62 | — | Imported | 2026-05-06 |
| 22 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, unquantized) | 275.19 | — | Imported | 2026-05-06 |
| 23 | trl-internal-testing/dummy-GPT2-correct-vocab on ['Tesla T4'] (pytorch, unquantized) | 274.00 | — | Imported | 2026-05-06 |
| 24 | EleutherAI/pythia-70m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 273.48 | — | Imported | 2026-05-06 |
| 25 | trl-internal-testing/dummy-GPT2-correct-vocab on ['Tesla T4'] (pytorch, unquantized) | 272.46 | — | Imported | 2026-05-06 |
| 26 | EleutherAI/pythia-70m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 259.01 | — | Imported | 2026-05-06 |
| 27 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, gptq) | 257.32 | — | Imported | 2026-05-06 |
| 28 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, gptq) | 252.64 | — | Imported | 2026-05-06 |
| 29 | trl-internal-testing/dummy-GPT2-correct-vocab on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 252.49 | — | Imported | 2026-05-06 |
| 30 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 251.47 | — | Imported | 2026-05-06 |
| 31 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, gptq) | 248.53 | — | Imported | 2026-05-06 |
| 32 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, awq) | 247.70 | — | Imported | 2026-05-06 |
| 33 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, unquantized) | 245.94 | — | Imported | 2026-05-06 |
| 34 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, gptq) | 244.91 | — | Imported | 2026-05-06 |
| 35 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, awq) | 244.42 | — | Imported | 2026-05-06 |
| 36 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, unquantized) | 243.50 | — | Imported | 2026-05-06 |
| 37 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, awq) | 243.38 | — | Imported | 2026-05-06 |
| 38 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, unquantized) | 241.97 | — | Imported | 2026-05-06 |
| 39 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, unquantized) | 241.92 | — | Imported | 2026-05-06 |
| 40 | EleutherAI/pythia-70m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 241.65 | — | Imported | 2026-05-06 |
| 41 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 241.60 | — | Imported | 2026-05-06 |
| 42 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 241.14 | — | Imported | 2026-05-06 |
| 43 | trl-internal-testing/dummy-GPT2-correct-vocab on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 241.08 | — | Imported | 2026-05-06 |
| 44 | trl-internal-testing/dummy-GPT2-correct-vocab on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 240.43 | — | Imported | 2026-05-06 |
| 45 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, awq) | 239.60 | — | Imported | 2026-05-06 |
| 46 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, awq) | 237.62 | — | Imported | 2026-05-06 |
| 47 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, gptq) | 236.81 | — | Imported | 2026-05-06 |
| 48 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, awq) | 236.36 | — | Imported | 2026-05-06 |
| 49 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, awq) | 235.25 | — | Imported | 2026-05-06 |
| 50 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, gptq) | 234.40 | — | Imported | 2026-05-06 |
| 51 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 233.94 | — | Imported | 2026-05-06 |
| 52 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, awq) | 232.91 | — | Imported | 2026-05-06 |
| 53 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, awq) | 232.72 | — | Imported | 2026-05-06 |
| 54 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 232.19 | — | Imported | 2026-05-06 |
| 55 | EleutherAI/pythia-70m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 232.02 | — | Imported | 2026-05-06 |
| 56 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, awq) | 230.74 | — | Imported | 2026-05-06 |
| 57 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, unquantized) | 230.18 | — | Imported | 2026-05-06 |
| 58 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, awq) | 229.92 | — | Imported | 2026-05-06 |
| 59 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, awq) | 226.31 | — | Imported | 2026-05-06 |
| 60 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 224.78 | — | Imported | 2026-05-06 |
| 61 | EleutherAI/pythia-70m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 224.34 | — | Imported | 2026-05-06 |
| 62 | trl-internal-testing/dummy-GPT2-correct-vocab on ['Tesla T4'] (pytorch, unquantized) | 222.17 | — | Imported | 2026-05-06 |
| 63 | trl-internal-testing/dummy-GPT2-correct-vocab on ['Tesla T4'] (pytorch, unquantized) | 220.22 | — | Imported | 2026-05-06 |
| 64 | trl-internal-testing/dummy-GPT2-correct-vocab on ['Tesla T4'] (pytorch, unquantized) | 216.96 | — | Imported | 2026-05-06 |
| 65 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, unquantized) | 215.47 | — | Imported | 2026-05-06 |
| 66 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, unquantized) | 215.46 | — | Imported | 2026-05-06 |
| 67 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 215.31 | — | Imported | 2026-05-06 |
| 68 | trl-internal-testing/dummy-GPT2-correct-vocab on ['Tesla T4'] (pytorch, unquantized) | 214.42 | — | Imported | 2026-05-06 |
| 69 | EleutherAI/pythia-70m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 213.64 | — | Imported | 2026-05-06 |
| 70 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, gptq) | 211.67 | — | Imported | 2026-05-06 |
| 71 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 211.31 | — | Imported | 2026-05-06 |
| 72 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, unquantized) | 210.45 | — | Imported | 2026-05-06 |
| 73 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, gptq) | 209.89 | — | Imported | 2026-05-06 |
| 74 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, gptq) | 208.85 | — | Imported | 2026-05-06 |
| 75 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 208.81 | — | Imported | 2026-05-06 |
| 76 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, gptq) | 206.67 | — | Imported | 2026-05-06 |
| 77 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 206.37 | — | Imported | 2026-05-06 |
| 78 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 206.17 | — | Imported | 2026-05-06 |
| 79 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 205.64 | — | Imported | 2026-05-06 |
| 80 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 205.62 | — | Imported | 2026-05-06 |
| 81 | distilbert/distilgpt2 on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 205.01 | — | Imported | 2026-05-06 |
| 82 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, awq) | 204.62 | — | Imported | 2026-05-06 |
| 83 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 204.29 | — | Imported | 2026-05-06 |
| 84 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, gptq) | 203.74 | — | Imported | 2026-05-06 |
| 85 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 201.96 | — | Imported | 2026-05-06 |
| 86 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, gptq) | 201.34 | — | Imported | 2026-05-06 |
| 87 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, gptq) | 201.25 | — | Imported | 2026-05-06 |
| 88 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, unquantized) | 201.24 | — | Imported | 2026-05-06 |
| 89 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, awq) | 199.64 | — | Imported | 2026-05-06 |
| 90 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, awq) | 199.54 | — | Imported | 2026-05-06 |
| 91 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 198.88 | — | Imported | 2026-05-06 |
| 92 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 198.67 | — | Imported | 2026-05-06 |
| 93 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 198.12 | — | Imported | 2026-05-06 |
| 94 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, gptq) | 198.05 | — | Imported | 2026-05-06 |
| 95 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, unquantized) | 197.55 | — | Imported | 2026-05-06 |
| 96 | distilbert/distilgpt2 on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 197.26 | — | Imported | 2026-05-06 |
| 97 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 196.81 | — | Imported | 2026-05-06 |
| 98 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 196.79 | — | Imported | 2026-05-06 |
| 99 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 196.07 | — | Imported | 2026-05-06 |
| 100 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 195.76 | — | Imported | 2026-05-06 |
| 101 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, awq) | 194.98 | — | Imported | 2026-05-06 |
| 102 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, gptq) | 194.36 | — | Imported | 2026-05-06 |
| 103 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, unquantized) | 192.58 | — | Imported | 2026-05-06 |
| 104 | distilbert/distilgpt2 on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 192.34 | — | Imported | 2026-05-06 |
| 105 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 192.29 | — | Imported | 2026-05-06 |
| 106 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 192.06 | — | Imported | 2026-05-06 |
| 107 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 191.63 | — | Imported | 2026-05-06 |
| 108 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 191.42 | — | Imported | 2026-05-06 |
| 109 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 191.16 | — | Imported | 2026-05-06 |
| 110 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 190.81 | — | Imported | 2026-05-06 |
| 111 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 190.79 | — | Imported | 2026-05-06 |
| 112 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, gptq) | 190.67 | — | Imported | 2026-05-06 |
| 113 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 189.08 | — | Imported | 2026-05-06 |
| 114 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, awq) | 188.69 | — | Imported | 2026-05-06 |
| 115 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, awq) | 188.49 | — | Imported | 2026-05-06 |
| 116 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, gptq) | 187.98 | — | Imported | 2026-05-06 |
| 117 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 187.87 | — | Imported | 2026-05-06 |
| 118 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, awq) | 187.22 | — | Imported | 2026-05-06 |
| 119 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 186.93 | — | Imported | 2026-05-06 |
| 120 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, unquantized) | 186.93 | — | Imported | 2026-05-06 |
| 121 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 186.74 | — | Imported | 2026-05-06 |
| 122 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 186.39 | — | Imported | 2026-05-06 |
| 123 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 186.19 | — | Imported | 2026-05-06 |
| 124 | distilbert/distilgpt2 on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 185.49 | — | Imported | 2026-05-06 |
| 125 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, awq) | 185.12 | — | Imported | 2026-05-06 |
| 126 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 184.65 | — | Imported | 2026-05-06 |
| 127 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, unquantized) | 183.85 | — | Imported | 2026-05-06 |
| 128 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 183.20 | — | Imported | 2026-05-06 |
| 129 | distilbert/distilgpt2 on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 183.16 | — | Imported | 2026-05-06 |
| 130 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 182.21 | — | Imported | 2026-05-06 |
| 131 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, unquantized) | 181.55 | — | Imported | 2026-05-06 |
| 132 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, unquantized) | 181.51 | — | Imported | 2026-05-06 |
| 133 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, gptq) | 178.26 | — | Imported | 2026-05-06 |
| 134 | distilbert/distilgpt2 on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 176.87 | — | Imported | 2026-05-06 |
| 135 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, gptq) | 176.34 | — | Imported | 2026-05-06 |
| 136 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 175.13 | — | Imported | 2026-05-06 |
| 137 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, unquantized) | 174.75 | — | Imported | 2026-05-06 |
| 138 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 174.30 | — | Imported | 2026-05-06 |
| 139 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 173.96 | — | Imported | 2026-05-06 |
| 140 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, unquantized) | 172.21 | — | Imported | 2026-05-06 |
| 141 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, unquantized) | 172.10 | — | Imported | 2026-05-06 |
| 142 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 172.06 | — | Imported | 2026-05-06 |
| 143 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 171.28 | — | Imported | 2026-05-06 |
| 144 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 170.20 | — | Imported | 2026-05-06 |
| 145 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 169.62 | — | Imported | 2026-05-06 |
| 146 | facebook/opt-125m on ['NVIDIA A100-SXM4-80GB'] (pytorch, unquantized) | 169.28 | — | Imported | 2026-05-06 |
| 147 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 164.81 | — | Imported | 2026-05-06 |
| 148 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, unquantized) | 164.72 | — | Imported | 2026-05-06 |
| 149 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 164.69 | — | Imported | 2026-05-06 |
| 150 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 164.45 | — | Imported | 2026-05-06 |
| 151 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, gptq) | 163.65 | — | Imported | 2026-05-06 |
| 152 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 162.99 | — | Imported | 2026-05-06 |
| 153 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, gptq) | 162.52 | — | Imported | 2026-05-06 |
| 154 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 162.39 | — | Imported | 2026-05-06 |
| 155 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, gptq) | 161.37 | — | Imported | 2026-05-06 |
| 156 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, gptq) | 161.33 | — | Imported | 2026-05-06 |
| 157 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, unquantized) | 160.17 | — | Imported | 2026-05-06 |
| 158 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, unquantized) | 159.81 | — | Imported | 2026-05-06 |
| 159 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, bnb) | 159.57 | — | Imported | 2026-05-06 |
| 160 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, gptq) | 159.19 | — | Imported | 2026-05-06 |
| 161 | facebook/opt-125m on ['Tesla T4'] (pytorch, unquantized) | 158.80 | — | Imported | 2026-05-06 |
| 162 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 158.40 | — | Imported | 2026-05-06 |
| 163 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 158.29 | — | Imported | 2026-05-06 |
| 164 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 157.90 | — | Imported | 2026-05-06 |
| 165 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 157.66 | — | Imported | 2026-05-06 |
| 166 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 157.59 | — | Imported | 2026-05-06 |
| 167 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 156.65 | — | Imported | 2026-05-06 |
| 168 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 155.89 | — | Imported | 2026-05-06 |
| 169 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 155.48 | — | Imported | 2026-05-06 |
| 170 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 155.34 | — | Imported | 2026-05-06 |
| 171 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, torchao) | 154.77 | — | Imported | 2026-05-06 |
| 172 | facebook/opt-125m on ['Tesla T4'] (pytorch, unquantized) | 154.72 | — | Imported | 2026-05-06 |
| 173 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 154.31 | — | Imported | 2026-05-06 |
| 174 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 153.91 | — | Imported | 2026-05-06 |
| 175 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 153.48 | — | Imported | 2026-05-06 |
| 176 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 153.27 | — | Imported | 2026-05-06 |
| 177 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 153.14 | — | Imported | 2026-05-06 |
| 178 | facebook/opt-125m on ['NVIDIA A100-SXM4-80GB'] (pytorch, unquantized) | 153.14 | — | Imported | 2026-05-06 |
| 179 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 152.67 | — | Imported | 2026-05-06 |
| 180 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 152.51 | — | Imported | 2026-05-06 |
| 181 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 152.28 | — | Imported | 2026-05-06 |
| 182 | openai-community/gpt2 on ['Tesla T4'] (pytorch, gptq) | 151.81 | — | Imported | 2026-05-06 |
| 183 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 151.81 | — | Imported | 2026-05-06 |
| 184 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 151.81 | — | Imported | 2026-05-06 |
| 185 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 151.79 | — | Imported | 2026-05-06 |
| 186 | openai-community/gpt2 on ['Tesla T4'] (pytorch, gptq) | 151.37 | — | Imported | 2026-05-06 |
| 187 | facebook/opt-125m on ['NVIDIA A100-SXM4-80GB'] (pytorch, unquantized) | 151.24 | — | Imported | 2026-05-06 |
| 188 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, unquantized) | 151.07 | — | Imported | 2026-05-06 |
| 189 | facebook/opt-125m on ['Tesla T4'] (pytorch, awq) | 151.04 | — | Imported | 2026-05-06 |
| 190 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 150.83 | — | Imported | 2026-05-06 |
| 191 | facebook/opt-125m on ['Tesla T4'] (pytorch, gptq) | 150.80 | — | Imported | 2026-05-06 |
| 192 | datificate/gpt2-small-spanish on ['NVIDIA A10G'] (pytorch, unquantized) | 150.79 | — | Imported | 2026-05-06 |
| 193 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 150.56 | — | Imported | 2026-05-06 |
| 194 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 150.45 | — | Imported | 2026-05-06 |
| 195 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 150.19 | — | Imported | 2026-05-06 |
| 196 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 150.16 | — | Imported | 2026-05-06 |
| 197 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, bnb) | 149.99 | — | Imported | 2026-05-06 |
| 198 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, gptq) | 149.99 | — | Imported | 2026-05-06 |
| 199 | facebook/opt-125m on ['Tesla T4'] (pytorch, awq) | 149.81 | — | Imported | 2026-05-06 |
| 200 | EleutherAI/gpt-neo-125m on ['NVIDIA A100-SXM4-80GB'] (pytorch, unquantized) | 149.46 | — | Imported | 2026-05-06 |
| 201 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 149.24 | — | Imported | 2026-05-06 |
| 202 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, gptq) | 149.00 | — | Imported | 2026-05-06 |
| 203 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 148.75 | — | Imported | 2026-05-06 |
| 204 | datificate/gpt2-small-spanish on ['NVIDIA A10G'] (pytorch, unquantized) | 148.65 | — | Imported | 2026-05-06 |
| 205 | openai-community/gpt2 on ['Tesla T4'] (pytorch, gptq) | 148.61 | — | Imported | 2026-05-06 |
| 206 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, bnb) | 148.27 | — | Imported | 2026-05-06 |
| 207 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, gptq) | 148.25 | — | Imported | 2026-05-06 |
| 208 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 148.11 | — | Imported | 2026-05-06 |
| 209 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, gptq) | 148.03 | — | Imported | 2026-05-06 |
| 210 | openai-community/gpt2 on ['Tesla T4'] (pytorch, gptq) | 147.72 | — | Imported | 2026-05-06 |
| 211 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 147.54 | — | Imported | 2026-05-06 |
| 212 | openai-community/gpt2 on ['NVIDIA A100-SXM4-80GB'] (pytorch, unquantized) | 147.37 | — | Imported | 2026-05-06 |
| 213 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, gptq) | 147.30 | — | Imported | 2026-05-06 |
| 214 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, gptq) | 147.03 | — | Imported | 2026-05-06 |
| 215 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, gptq) | 146.90 | — | Imported | 2026-05-06 |
| 216 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 146.17 | — | Imported | 2026-05-06 |
| 217 | EleutherAI/gpt-neo-125m on ['NVIDIA A100-SXM4-80GB'] (pytorch, unquantized) | 145.79 | — | Imported | 2026-05-06 |
| 218 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 145.58 | — | Imported | 2026-05-06 |
| 219 | datificate/gpt2-small-spanish on ['NVIDIA A10G'] (pytorch, unquantized) | 145.47 | — | Imported | 2026-05-06 |
| 220 | facebook/opt-125m on ['Tesla T4'] (pytorch, gptq) | 145.05 | — | Imported | 2026-05-06 |
| 221 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, gptq) | 144.97 | — | Imported | 2026-05-06 |
| 222 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 144.46 | — | Imported | 2026-05-06 |
| 223 | facebook/opt-125m on ['NVIDIA A100-SXM4-80GB'] (pytorch, unquantized) | 144.45 | — | Imported | 2026-05-06 |
| 224 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 144.41 | — | Imported | 2026-05-06 |
| 225 | datificate/gpt2-small-spanish on ['Tesla T4'] (pytorch, gptq) | 144.24 | — | Imported | 2026-05-06 |
| 226 | datificate/gpt2-small-spanish on ['Tesla T4'] (pytorch, unquantized) | 143.95 | — | Imported | 2026-05-06 |
| 227 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 143.81 | — | Imported | 2026-05-06 |
| 228 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 143.76 | — | Imported | 2026-05-06 |
| 229 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 143.62 | — | Imported | 2026-05-06 |
| 230 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 143.59 | — | Imported | 2026-05-06 |
| 231 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 143.05 | — | Imported | 2026-05-06 |
| 232 | openai-community/gpt2 on ['Tesla T4'] (pytorch, unquantized) | 142.97 | — | Imported | 2026-05-06 |
| 233 | datificate/gpt2-small-spanish on ['Tesla T4'] (pytorch, gptq) | 142.84 | — | Imported | 2026-05-06 |
| 234 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 142.84 | — | Imported | 2026-05-06 |
| 235 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 142.43 | — | Imported | 2026-05-06 |
| 236 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 142.34 | — | Imported | 2026-05-06 |
| 237 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, bnb) | 142.15 | — | Imported | 2026-05-06 |
| 238 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, bnb) | 141.70 | — | Imported | 2026-05-06 |
| 239 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, awq) | 141.47 | — | Imported | 2026-05-06 |
| 240 | datificate/gpt2-small-spanish on ['Tesla T4'] (pytorch, unquantized) | 141.39 | — | Imported | 2026-05-06 |
| 241 | facebook/opt-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 140.93 | — | Imported | 2026-05-06 |
| 242 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, awq) | 140.56 | — | Imported | 2026-05-06 |
| 243 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, gptq) | 140.33 | — | Imported | 2026-05-06 |
| 244 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, gptq) | 140.05 | — | Imported | 2026-05-06 |
| 245 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, gptq) | 139.65 | — | Imported | 2026-05-06 |
| 246 | openai-community/gpt2 on ['Tesla T4'] (pytorch, unquantized) | 139.57 | — | Imported | 2026-05-06 |
| 247 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 139.43 | — | Imported | 2026-05-06 |
| 248 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, awq) | 139.27 | — | Imported | 2026-05-06 |
| 249 | trl-internal-testing/dummy-GPT2-correct-vocab on ['NVIDIA A10G'] (pytorch, bnb) | 139.04 | — | Imported | 2026-05-06 |
| 250 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 138.92 | — | Imported | 2026-05-06 |
| 251 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, awq) | 138.20 | — | Imported | 2026-05-06 |
| 252 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, torchao) | 137.76 | — | Imported | 2026-05-06 |
| 253 | datificate/gpt2-small-spanish on ['NVIDIA A10G'] (pytorch, unquantized) | 137.54 | — | Imported | 2026-05-06 |
| 254 | datificate/gpt2-small-spanish on ['NVIDIA A10G'] (pytorch, unquantized) | 137.28 | — | Imported | 2026-05-06 |
| 255 | facebook/opt-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 137.21 | — | Imported | 2026-05-06 |
| 256 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, awq) | 136.39 | — | Imported | 2026-05-06 |
| 257 | facebook/opt-125m on ['Tesla T4'] (pytorch, awq) | 136.27 | — | Imported | 2026-05-06 |
| 258 | facebook/opt-125m on ['Tesla T4'] (pytorch, unquantized) | 136.25 | — | Imported | 2026-05-06 |
| 259 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 136.06 | — | Imported | 2026-05-06 |
| 260 | openai-community/gpt2 on ['Tesla T4'] (pytorch, awq) | 135.88 | — | Imported | 2026-05-06 |
| 261 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 135.86 | — | Imported | 2026-05-06 |
| 262 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 135.76 | — | Imported | 2026-05-06 |
| 263 | openai-community/gpt2 on ['Tesla T4'] (pytorch, awq) | 135.74 | — | Imported | 2026-05-06 |
| 264 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 135.67 | — | Imported | 2026-05-06 |
| 265 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, torchao) | 134.84 | — | Imported | 2026-05-06 |
| 266 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 134.70 | — | Imported | 2026-05-06 |
| 267 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 134.66 | — | Imported | 2026-05-06 |
| 268 | facebook/opt-125m on ['Tesla T4'] (pytorch, unquantized) | 134.15 | — | Imported | 2026-05-06 |
| 269 | distilbert/distilgpt2 on Intel(R) Xeon(R) Platinum 8488C (onnxruntime, unquantized) | 133.14 | — | Imported | 2026-05-06 |
| 270 | openai-community/gpt2 on ['Tesla T4'] (pytorch, awq) | 132.87 | — | Imported | 2026-05-06 |
| 271 | openai-community/gpt2 on ['Tesla T4'] (pytorch, awq) | 132.80 | — | Imported | 2026-05-06 |
| 272 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, awq) | 132.80 | — | Imported | 2026-05-06 |
| 273 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 132.74 | — | Imported | 2026-05-06 |
| 274 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 132.60 | — | Imported | 2026-05-06 |
| 275 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 132.45 | — | Imported | 2026-05-06 |
| 276 | facebook/opt-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 132.41 | — | Imported | 2026-05-06 |
| 277 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 132.10 | — | Imported | 2026-05-06 |
| 278 | distilbert/distilgpt2 on Intel(R) Xeon(R) Platinum 8488C (onnxruntime, unquantized) | 132.08 | — | Imported | 2026-05-06 |
| 279 | openai-community/gpt2 on ['Tesla T4'] (pytorch, unquantized) | 131.71 | — | Imported | 2026-05-06 |
| 280 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, torchao) | 131.69 | — | Imported | 2026-05-06 |
| 281 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, gptq) | 131.63 | — | Imported | 2026-05-06 |
| 282 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 131.49 | — | Imported | 2026-05-06 |
| 283 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 130.62 | — | Imported | 2026-05-06 |
| 284 | facebook/opt-125m on ['Tesla T4'] (pytorch, unquantized) | 130.49 | — | Imported | 2026-05-06 |
| 285 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, awq) | 130.40 | — | Imported | 2026-05-06 |
| 286 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, bnb) | 130.34 | — | Imported | 2026-05-06 |
| 287 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 130.28 | — | Imported | 2026-05-06 |
| 288 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 130.10 | — | Imported | 2026-05-06 |
| 289 | EleutherAI/pythia-160m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 130.09 | — | Imported | 2026-05-06 |
| 290 | openai-community/gpt2 on ['Tesla T4'] (pytorch, unquantized) | 130.07 | — | Imported | 2026-05-06 |
| 291 | facebook/opt-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 129.90 | — | Imported | 2026-05-06 |
| 292 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, bnb) | 129.72 | — | Imported | 2026-05-06 |
| 293 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 129.26 | — | Imported | 2026-05-06 |
| 294 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, gptq) | 129.16 | — | Imported | 2026-05-06 |
| 295 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, gptq) | 129.11 | — | Imported | 2026-05-06 |
| 296 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 129.08 | — | Imported | 2026-05-06 |
| 297 | facebook/opt-125m on ['Tesla T4'] (pytorch, torchao) | 128.83 | — | Imported | 2026-05-06 |
| 298 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 128.82 | — | Imported | 2026-05-06 |
| 299 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 128.48 | — | Imported | 2026-05-06 |
| 300 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 128.40 | — | Imported | 2026-05-06 |
| 301 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 128.14 | — | Imported | 2026-05-06 |
| 302 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, unquantized) | 127.61 | — | Imported | 2026-05-06 |
| 303 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 127.18 | — | Imported | 2026-05-06 |
| 304 | facebook/opt-125m on ['Tesla T4'] (pytorch, unquantized) | 127.15 | — | Imported | 2026-05-06 |
| 305 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 127.15 | — | Imported | 2026-05-06 |
| 306 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 127.05 | — | Imported | 2026-05-06 |
| 307 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 126.39 | — | Imported | 2026-05-06 |
| 308 | EleutherAI/gpt-neo-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 126.16 | — | Imported | 2026-05-06 |
| 309 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 126.11 | — | Imported | 2026-05-06 |
| 310 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, gptq) | 126.11 | — | Imported | 2026-05-06 |
| 311 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, awq) | 126.03 | — | Imported | 2026-05-06 |
| 312 | facebook/opt-125m on ['Tesla T4'] (pytorch, unquantized) | 125.64 | — | Imported | 2026-05-06 |
| 313 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 125.15 | — | Imported | 2026-05-06 |
| 314 | EleutherAI/gpt-neo-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 125.11 | — | Imported | 2026-05-06 |
| 315 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 124.89 | — | Imported | 2026-05-06 |
| 316 | EleutherAI/gpt-neo-125m on ['NVIDIA A100-SXM4-80GB'] (pytorch, unquantized) | 124.60 | — | Imported | 2026-05-06 |
| 317 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 123.97 | — | Imported | 2026-05-06 |
| 318 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 123.94 | — | Imported | 2026-05-06 |
| 319 | openai-community/gpt2 on ['Tesla T4'] (pytorch, unquantized) | 123.64 | — | Imported | 2026-05-06 |
| 320 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, bnb) | 123.57 | — | Imported | 2026-05-06 |
| 321 | openai-community/gpt2 on ['Tesla T4'] (pytorch, unquantized) | 123.19 | — | Imported | 2026-05-06 |
| 322 | facebook/opt-125m on ['Tesla T4'] (pytorch, awq) | 122.82 | — | Imported | 2026-05-06 |
| 323 | distilbert/distilgpt2 on Intel(R) Xeon(R) Platinum 8488C (onnxruntime, unquantized) | 122.81 | — | Imported | 2026-05-06 |
| 324 | facebook/opt-125m on ['Tesla T4'] (pytorch, unquantized) | 122.63 | — | Imported | 2026-05-06 |
| 325 | EleutherAI/pythia-160m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 122.57 | — | Imported | 2026-05-06 |
| 326 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 122.41 | — | Imported | 2026-05-06 |
| 327 | distilbert/distilgpt2 on Intel(R) Xeon(R) Platinum 8488C (onnxruntime, unquantized) | 122.27 | — | Imported | 2026-05-06 |
| 328 | facebook/opt-125m on ['Tesla T4'] (pytorch, unquantized) | 121.97 | — | Imported | 2026-05-06 |
| 329 | EleutherAI/gpt-neo-125m on ['NVIDIA A100-SXM4-80GB'] (pytorch, unquantized) | 121.82 | — | Imported | 2026-05-06 |
| 330 | EleutherAI/gpt-neo-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 121.38 | — | Imported | 2026-05-06 |
| 331 | distilbert/distilgpt2 on Intel(R) Xeon(R) Platinum 8488C (onnxruntime, unquantized) | 121.38 | — | Imported | 2026-05-06 |
| 332 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, unquantized) | 121.11 | — | Imported | 2026-05-06 |
| 333 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 120.42 | — | Imported | 2026-05-06 |
| 334 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, bnb) | 120.29 | — | Imported | 2026-05-06 |
| 335 | distilbert/distilgpt2 on ['NVIDIA A10G'] (pytorch, bnb) | 120.20 | — | Imported | 2026-05-06 |
| 336 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, bnb) | 120.01 | — | Imported | 2026-05-06 |
| 337 | openai-community/gpt2 on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 119.92 | — | Imported | 2026-05-06 |
| 338 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 119.79 | — | Imported | 2026-05-06 |
| 339 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, gptq) | 119.55 | — | Imported | 2026-05-06 |
| 340 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 119.48 | — | Imported | 2026-05-06 |
| 341 | EleutherAI/gpt-neo-125m on ['NVIDIA A100-SXM4-80GB'] (pytorch, unquantized) | 119.46 | — | Imported | 2026-05-06 |
| 342 | datificate/gpt2-small-spanish on ['NVIDIA A10G'] (pytorch, unquantized) | 119.28 | — | Imported | 2026-05-06 |
| 343 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, bnb) | 119.27 | — | Imported | 2026-05-06 |
| 344 | facebook/opt-125m on ['Tesla T4'] (pytorch, gptq) | 119.11 | — | Imported | 2026-05-06 |
| 345 | distilbert/distilgpt2 on Intel(R) Xeon(R) Platinum 8488C (onnxruntime, unquantized) | 118.89 | — | Imported | 2026-05-06 |
| 346 | facebook/opt-125m on ['Tesla T4'] (pytorch, gptq) | 118.08 | — | Imported | 2026-05-06 |
| 347 | facebook/opt-125m on ['Tesla T4'] (pytorch, gptq) | 117.81 | — | Imported | 2026-05-06 |
| 348 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, gptq) | 117.74 | — | Imported | 2026-05-06 |
| 349 | EleutherAI/pythia-160m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 117.68 | — | Imported | 2026-05-06 |
| 350 | datificate/gpt2-small-spanish on ['NVIDIA A10G'] (pytorch, unquantized) | 117.59 | — | Imported | 2026-05-06 |
| 351 | openai-community/gpt2 on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 117.53 | — | Imported | 2026-05-06 |
| 352 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, torchao) | 117.32 | — | Imported | 2026-05-06 |
| 353 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 117.11 | — | Imported | 2026-05-06 |
| 354 | facebook/opt-125m on ['Tesla T4'] (pytorch, gptq) | 117.01 | — | Imported | 2026-05-06 |
| 355 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 116.46 | — | Imported | 2026-05-06 |
| 356 | EleutherAI/pythia-70m on ['NVIDIA A100-SXM4-80GB'] (pytorch, gptq) | 116.30 | — | Imported | 2026-05-06 |
| 357 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, gptq) | 116.04 | — | Imported | 2026-05-06 |
| 358 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 115.98 | — | Imported | 2026-05-06 |
| 359 | EleutherAI/pythia-70m on ['NVIDIA A100-SXM4-80GB'] (pytorch, gptq) | 115.95 | — | Imported | 2026-05-06 |
| 360 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, unquantized) | 115.82 | — | Imported | 2026-05-06 |
| 361 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, gptq) | 115.81 | — | Imported | 2026-05-06 |
| 362 | openai-community/gpt2 on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 115.68 | — | Imported | 2026-05-06 |
| 363 | EleutherAI/gpt-neo-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 115.67 | — | Imported | 2026-05-06 |
| 364 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, gptq) | 115.06 | — | Imported | 2026-05-06 |
| 365 | facebook/opt-125m on ['NVIDIA A10G'] (pytorch, awq) | 115.00 | — | Imported | 2026-05-06 |
| 366 | datificate/gpt2-small-spanish on ['NVIDIA A10G'] (pytorch, unquantized) | 114.96 | — | Imported | 2026-05-06 |
| 367 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 114.75 | — | Imported | 2026-05-06 |
| 368 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 114.61 | — | Imported | 2026-05-06 |
| 369 | EleutherAI/gpt-neo-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 114.47 | — | Imported | 2026-05-06 |
| 370 | EleutherAI/gpt-neo-125m on ['Tesla T4'] (pytorch, unquantized) | 114.38 | — | Imported | 2026-05-06 |
| 371 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, gptq) | 114.16 | — | Imported | 2026-05-06 |
| 372 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 113.87 | — | Imported | 2026-05-06 |
| 373 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, gptq) | 113.86 | — | Imported | 2026-05-06 |
| 374 | facebook/opt-125m on ['Tesla T4'] (pytorch, unquantized) | 113.40 | — | Imported | 2026-05-06 |
| 375 | facebook/opt-125m on ['Tesla T4'] (pytorch, unquantized) | 113.33 | — | Imported | 2026-05-06 |
| 376 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, awq) | 113.31 | — | Imported | 2026-05-06 |
| 377 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, unquantized) | 113.23 | — | Imported | 2026-05-06 |
| 378 | facebook/opt-125m on ['Tesla T4'] (pytorch, awq) | 113.21 | — | Imported | 2026-05-06 |
| 379 | facebook/opt-125m on ['Tesla T4'] (pytorch, torchao) | 112.93 | — | Imported | 2026-05-06 |
| 380 | facebook/opt-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 112.83 | — | Imported | 2026-05-06 |
| 381 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, gptq) | 112.69 | — | Imported | 2026-05-06 |
| 382 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, awq) | 112.68 | — | Imported | 2026-05-06 |
| 383 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 112.49 | — | Imported | 2026-05-06 |
| 384 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, torchao) | 112.42 | — | Imported | 2026-05-06 |
| 385 | facebook/opt-125m on ['Tesla T4'] (pytorch, awq) | 112.41 | — | Imported | 2026-05-06 |
| 386 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, gptq) | 112.38 | — | Imported | 2026-05-06 |
| 387 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, bnb) | 112.35 | — | Imported | 2026-05-06 |
| 388 | openai-community/gpt2 on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 111.90 | — | Imported | 2026-05-06 |
| 389 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 111.77 | — | Imported | 2026-05-06 |
| 390 | trl-internal-testing/dummy-GPT2-correct-vocab on ['Tesla T4'] (pytorch, bnb) | 111.69 | — | Imported | 2026-05-06 |
| 391 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, unquantized) | 111.49 | — | Imported | 2026-05-06 |
| 392 | EleutherAI/gpt-neo-125m on ['Tesla T4'] (pytorch, unquantized) | 111.32 | — | Imported | 2026-05-06 |
| 393 | openai-community/gpt2 on ['Tesla T4'] (pytorch, unquantized) | 111.20 | — | Imported | 2026-05-06 |
| 394 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, unquantized) | 111.13 | — | Imported | 2026-05-06 |
| 395 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, gptq) | 110.88 | — | Imported | 2026-05-06 |
| 396 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, awq) | 110.81 | — | Imported | 2026-05-06 |
| 397 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, awq) | 110.73 | — | Imported | 2026-05-06 |
| 398 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, unquantized) | 110.63 | — | Imported | 2026-05-06 |
| 399 | openai-community/gpt2 on ['Tesla T4'] (pytorch, gptq) | 110.47 | — | Imported | 2026-05-06 |
| 400 | EleutherAI/pythia-160m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 110.46 | — | Imported | 2026-05-06 |
| 401 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, gptq) | 110.46 | — | Imported | 2026-05-06 |
| 402 | datificate/gpt2-small-spanish on ['Tesla T4'] (pytorch, unquantized) | 110.45 | — | Imported | 2026-05-06 |
| 403 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, gptq) | 110.40 | — | Imported | 2026-05-06 |
| 404 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, unquantized) | 110.30 | — | Imported | 2026-05-06 |
| 405 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, gptq) | 110.06 | — | Imported | 2026-05-06 |
| 406 | facebook/opt-125m on ['Tesla T4'] (pytorch, unquantized) | 109.81 | — | Imported | 2026-05-06 |
| 407 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, gptq) | 109.75 | — | Imported | 2026-05-06 |
| 408 | openai-community/gpt2 on ['Tesla T4'] (pytorch, unquantized) | 109.70 | — | Imported | 2026-05-06 |
| 409 | EleutherAI/gpt-neo-125m on ['Tesla T4'] (pytorch, unquantized) | 109.65 | — | Imported | 2026-05-06 |
| 410 | facebook/opt-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 109.59 | — | Imported | 2026-05-06 |
| 411 | openai-community/gpt2 on ['Tesla T4'] (pytorch, gptq) | 109.36 | — | Imported | 2026-05-06 |
| 412 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, gptq) | 109.12 | — | Imported | 2026-05-06 |
| 413 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, awq) | 109.11 | — | Imported | 2026-05-06 |
| 414 | EleutherAI/gpt-neo-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 109.07 | — | Imported | 2026-05-06 |
| 415 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, gptq) | 109.01 | — | Imported | 2026-05-06 |
| 416 | datificate/gpt2-small-spanish on ['Tesla T4'] (pytorch, gptq) | 108.90 | — | Imported | 2026-05-06 |
| 417 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, awq) | 108.87 | — | Imported | 2026-05-06 |
| 418 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, awq) | 108.76 | — | Imported | 2026-05-06 |
| 419 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, gptq) | 108.63 | — | Imported | 2026-05-06 |
| 420 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 108.62 | — | Imported | 2026-05-06 |
| 421 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, awq) | 108.62 | — | Imported | 2026-05-06 |
| 422 | openai-community/gpt2 on ['NVIDIA A10G'] (pytorch, awq) | 108.61 | — | Imported | 2026-05-06 |
| 423 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, bnb) | 108.54 | — | Imported | 2026-05-06 |
| 424 | datificate/gpt2-small-spanish on ['Tesla T4'] (pytorch, unquantized) | 108.51 | — | Imported | 2026-05-06 |
| 425 | openai-community/gpt2 on ['Tesla T4'] (pytorch, gptq) | 108.30 | — | Imported | 2026-05-06 |
| 426 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, unquantized) | 108.29 | — | Imported | 2026-05-06 |
| 427 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, awq) | 108.07 | — | Imported | 2026-05-06 |
| 428 | datificate/gpt2-small-spanish on ['Tesla T4'] (pytorch, gptq) | 108.03 | — | Imported | 2026-05-06 |
| 429 | openai-community/gpt2 on ['Tesla T4'] (pytorch, torchao) | 107.73 | — | Imported | 2026-05-06 |
| 430 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, awq) | 107.72 | — | Imported | 2026-05-06 |
| 431 | openai-community/gpt2 on ['Tesla T4'] (pytorch, unquantized) | 107.68 | — | Imported | 2026-05-06 |
| 432 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, awq) | 107.65 | — | Imported | 2026-05-06 |
| 433 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, awq) | 107.65 | — | Imported | 2026-05-06 |
| 434 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, awq) | 107.59 | — | Imported | 2026-05-06 |
| 435 | openai-community/gpt2 on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 107.53 | — | Imported | 2026-05-06 |
| 436 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, unquantized) | 107.32 | — | Imported | 2026-05-06 |
| 437 | datificate/gpt2-small-spanish on ['Tesla T4'] (pytorch, unquantized) | 107.07 | — | Imported | 2026-05-06 |
| 438 | EleutherAI/pythia-70m on ['NVIDIA A100-SXM4-80GB'] (pytorch, gptq) | 107.00 | — | Imported | 2026-05-06 |
| 439 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 106.95 | — | Imported | 2026-05-06 |
| 440 | EleutherAI/gpt-neo-125m on ['Tesla T4'] (pytorch, unquantized) | 106.84 | — | Imported | 2026-05-06 |
| 441 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, awq) | 106.76 | — | Imported | 2026-05-06 |
| 442 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, bnb) | 106.41 | — | Imported | 2026-05-06 |
| 443 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, awq) | 106.41 | — | Imported | 2026-05-06 |
| 444 | openai-community/gpt2 on ['Tesla T4'] (pytorch, gptq) | 106.37 | — | Imported | 2026-05-06 |
| 445 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, awq) | 106.15 | — | Imported | 2026-05-06 |
| 446 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, awq) | 106.04 | — | Imported | 2026-05-06 |
| 447 | openai-community/gpt2 on ['Tesla T4'] (pytorch, unquantized) | 105.88 | — | Imported | 2026-05-06 |
| 448 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, awq) | 105.80 | — | Imported | 2026-05-06 |
| 449 | distilbert/distilgpt2 on ['Tesla T4'] (pytorch, bnb) | 105.75 | — | Imported | 2026-05-06 |
| 450 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, awq) | 105.19 | — | Imported | 2026-05-06 |
| 451 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 105.17 | — | Imported | 2026-05-06 |
| 452 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, gptq) | 105.12 | — | Imported | 2026-05-06 |
| 453 | openai-community/gpt2 on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 105.03 | — | Imported | 2026-05-06 |
| 454 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, gptq) | 104.96 | — | Imported | 2026-05-06 |
| 455 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, unquantized) | 104.77 | — | Imported | 2026-05-06 |
| 456 | facebook/opt-125m on ['Tesla T4'] (pytorch, awq) | 104.74 | — | Imported | 2026-05-06 |
| 457 | EleutherAI/pythia-70m on ['NVIDIA A100-SXM4-80GB'] (pytorch, gptq) | 104.63 | — | Imported | 2026-05-06 |
| 458 | EleutherAI/gpt-neo-125m on ['Tesla T4'] (pytorch, unquantized) | 104.62 | — | Imported | 2026-05-06 |
| 459 | openai-community/gpt2 on ['Tesla T4'] (pytorch, awq) | 104.12 | — | Imported | 2026-05-06 |
| 460 | EleutherAI/gpt-neo-125m on ['NVIDIA A10G'] (pytorch, unquantized) | 104.10 | — | Imported | 2026-05-06 |
| 461 | EleutherAI/gpt-neo-125m on ['Tesla T4'] (pytorch, awq) | 104.08 | — | Imported | 2026-05-06 |
| 462 | facebook/opt-125m on Intel(R) Xeon(R) Platinum 8488C (onnxruntime, unquantized) | 103.99 | — | Imported | 2026-05-06 |
| 463 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, awq) | 103.90 | — | Imported | 2026-05-06 |
| 464 | datificate/gpt2-small-spanish on ['Tesla T4'] (pytorch, unquantized) | 103.81 | — | Imported | 2026-05-06 |
| 465 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, unquantized) | 103.80 | — | Imported | 2026-05-06 |
| 466 | EleutherAI/gpt-neo-125m on ['Tesla T4'] (pytorch, awq) | 103.80 | — | Imported | 2026-05-06 |
| 467 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, unquantized) | 103.75 | — | Imported | 2026-05-06 |
| 468 | facebook/opt-125m on Intel(R) Xeon(R) Platinum 8488C (onnxruntime, unquantized) | 103.71 | — | Imported | 2026-05-06 |
| 469 | EleutherAI/pythia-160m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 102.96 | — | Imported | 2026-05-06 |
| 470 | EleutherAI/gpt-neo-125m on ['Tesla T4'] (pytorch, gptq) | 102.90 | — | Imported | 2026-05-06 |
| 471 | openai-community/gpt2 on ['Tesla T4'] (pytorch, awq) | 102.82 | — | Imported | 2026-05-06 |
| 472 | facebook/opt-125m on Intel(R) Xeon(R) Platinum 8488C (onnxruntime, unquantized) | 102.53 | — | Imported | 2026-05-06 |
| 473 | facebook/opt-125m on Intel(R) Xeon(R) Platinum 8488C (onnxruntime, unquantized) | 102.51 | — | Imported | 2026-05-06 |
| 474 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, bnb) | 102.49 | — | Imported | 2026-05-06 |
| 475 | openai-community/gpt2 on ['Tesla T4'] (pytorch, awq) | 102.22 | — | Imported | 2026-05-06 |
| 476 | openai-community/gpt2 on ['Tesla T4'] (pytorch, awq) | 102.01 | — | Imported | 2026-05-06 |
| 477 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, awq) | 101.91 | — | Imported | 2026-05-06 |
| 478 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, awq) | 101.76 | — | Imported | 2026-05-06 |
| 479 | EleutherAI/pythia-70m on ['NVIDIA A10G'] (pytorch, bnb) | 101.60 | — | Imported | 2026-05-06 |
| 480 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, awq) | 101.29 | — | Imported | 2026-05-06 |
| 481 | openai-community/gpt2 on ['Tesla T4'] (pytorch, unquantized) | 101.12 | — | Imported | 2026-05-06 |
| 482 | openai-community/gpt2 on ['Tesla T4'] (pytorch, torchao) | 100.90 | — | Imported | 2026-05-06 |
| 483 | EleutherAI/gpt-neo-125m on ['Tesla T4'] (pytorch, awq) | 100.79 | — | Imported | 2026-05-06 |
| 484 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, unquantized) | 100.65 | — | Imported | 2026-05-06 |
| 485 | EleutherAI/gpt-neo-125m on ['Tesla T4'] (pytorch, awq) | 100.13 | — | Imported | 2026-05-06 |
| 486 | trl-internal-testing/dummy-GPT2-correct-vocab on ['Tesla T4'] (pytorch, bnb) | 100.01 | — | Imported | 2026-05-06 |
| 487 | EleutherAI/pythia-70m on ['NVIDIA A100-SXM4-80GB'] (pytorch, bnb) | 99.98 | — | Imported | 2026-05-06 |
| 488 | openai-community/gpt2 on ['Tesla T4'] (pytorch, unquantized) | 99.84 | — | Imported | 2026-05-06 |
| 489 | EleutherAI/pythia-70m on ['Tesla T4'] (pytorch, bnb) | 99.50 | — | Imported | 2026-05-06 |
| 490 | EleutherAI/pythia-70m on ['NVIDIA A100-SXM4-80GB'] (pytorch, bnb) | 99.12 | — | Imported | 2026-05-06 |
| 491 | EleutherAI/gpt-neo-125m on ['Tesla T4'] (pytorch, awq) | 98.99 | — | Imported | 2026-05-06 |
| 492 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, unquantized) | 98.86 | — | Imported | 2026-05-06 |
| 493 | facebook/opt-350m on ['NVIDIA A100-SXM4-80GB'] (pytorch, unquantized) | 98.81 | — | Imported | 2026-05-06 |
| 494 | EleutherAI/pythia-160m on ['Tesla T4'] (pytorch, awq) | 98.46 | — | Imported | 2026-05-06 |
| 495 | EleutherAI/gpt-neo-125m on ['Tesla T4'] (pytorch, unquantized) | 98.40 | — | Imported | 2026-05-06 |
| 496 | EleutherAI/pythia-160m on ['NVIDIA A10G'] (pytorch, unquantized) | 98.37 | — | Imported | 2026-05-06 |
| 497 | EleutherAI/gpt-neo-125m on ['Tesla T4'] (pytorch, awq) | 97.93 | — | Imported | 2026-05-06 |
| 498 | EleutherAI/gpt-neo-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 97.67 | — | Imported | 2026-05-06 |
| 499 | EleutherAI/gpt-neo-125m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 97.48 | — | Imported | 2026-05-06 |
| 500 | EleutherAI/pythia-160m on Intel(R) Xeon(R) Platinum 8488C (pytorch, unquantized) | 97.18 | — | Imported | 2026-05-06 |
No matching rows.