GB10
106 records across 13 models (quants: BF16, IQ2_XXS, IQ2_XXS+Q5_K, NVFP4, Q4_0, Q4_K - Medium, Q4_K_M, Q8_0, UD-IQ4_XS, UD-Q4_K_M, UD-Q8_K_L).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GB10 | Falcon-H1-7B 7B | Q4_K_M | llama.cpp (CUDA) | 273.1 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Falcon-H1-7B 7B | BF16 | llama.cpp (CUDA) | 199.0 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Falcon-H1-7B 7B | Q4_K_M | llama.cpp (CUDA) | 187.7 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Falcon-H1-7B 7B | BF16 | llama.cpp (CUDA) | 80.0 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Gemma 4 12B | Q4_K_M | llama.cpp | 68.42 | – | – | – | – | 2026-10-12 | sourced | – | source |
| GB10 | Gemma 4 12B | Q4_K_M | llama.cpp | 67.31 | – | – | – | – | 2026-10-12 | sourced | – | source |
| GB10 | GLM-4.6 | IQ2_XXS+Q5_K | llama.cpp (CUDA) | 17.14 | – | – | – | 113664 | 2026-10-03 | community | – | source |
| GB10 | GLM-4.6 | IQ2_XXS+Q5_K | llama.cpp (CUDA) | 14.36 | – | – | – | 32768 | 2026-10-03 | community | – | source |
| GB10 | GLM-4.6 | IQ2_XXS+Q5_K | llama.cpp (CUDA) | 12.17 | – | – | – | 32768 | 2026-10-03 | community | – | source |
| GB10 | GLM-4.6 | IQ2_XXS+Q5_K | llama.cpp (CUDA) | 11.45 | – | – | – | 32768 | 2026-10-03 | community | – | source |
| GB10 | GLM-4.6 | IQ2_XXS+Q5_K | llama.cpp (CUDA) | 4.10 | 197 | – | – | 57600 | 2026-10-03 | community | – | source |
| GB10 | GLM-4.6 | IQ2_XXS+Q5_K | llama.cpp (CUDA) | 3.61 | 125 | – | – | 111900 | 2026-10-03 | community | – | source |
| GB10 | granite-4.0-h-tiny | Q4_K_M | llama.cpp (CUDA) | 551.2 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | granite-4.0-h-tiny | Q4_K_M | llama.cpp (CUDA) | 456.4 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | granite-4.0-h-tiny | BF16 | llama.cpp (CUDA) | 390.4 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | granite-4.0-h-tiny | BF16 | llama.cpp (CUDA) | 271.3 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 60.39 | 3321.91 | – | – | tg128 | 2026-07-14 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (CUDA) | 60.24 | 3310.48 | – | – | tg128 | 2026-01-20 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (CUDA) | 59.62 | 4016.46 | – | – | tg128 | 2026-03-30 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (CUDA) | 59.06 | 3306.61 | – | – | tg128 | 2026-03-30 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (CUDA) | 59.05 | 3954.97 | – | – | tg128 | 2026-03-30 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 58.51 | 2789.51 | – | – | tg128 | 2026-07-14 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (CUDA) | 58.38 | 3261.99 | – | – | tg128 | 2026-03-30 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (CUDA) | 58.14 | 3861.19 | – | – | tg128 | 2026-02-16 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (CUDA) | 58.13 | 3241.51 | – | – | tg128 | 2026-02-16 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (CUDA) | 57.21 | 3062.31 | – | – | tg128 | 2025-10-15 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (CUDA) | 56.74 | 3661.37 | – | – | tg128 | 2025-10-15 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (CUDA) | 54.91 | 3920.63 | – | – | tg128 | 2026-03-30 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (CUDA) | 54.39 | 3293.78 | – | – | tg128 | 2026-03-30 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 53.64 | 3279.89 | – | – | tg128 | 2026-03-15 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 53.21 | 3219.57 | – | – | tg128 | 2026-03-15 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 52.28 | 2737.79 | – | – | tg128 | 2026-03-15 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 51.7 | 2710.58 | – | – | tg128 | 2026-03-15 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 50.8 | 2665.61 | – | – | tg128 | 2026-01-20 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 48.42 | 2692.06 | – | – | tg128 | 2026-03-15 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 47.55 | 2731.93 | – | – | tg128 | 2026-03-14 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 46.67 | 3137.97 | – | – | tg128 | 2026-03-15 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (Vulkan) | 46.61 | 3171.16 | – | – | tg128 | 2026-03-14 | community | – | source |
| GB10 | llama 7B | Q4_0 | llama.cpp (CPU) | 24.08 | 313.01 | – | – | tg128 | 2026-01-20 | community | – | source |
| GB10 | mamba2-2.7b 2.7B | Q8_0 | llama.cpp (CUDA) | 246.7 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | mamba2-2.7b 2.7B | Q8_0 | llama.cpp (CUDA) | 98.4 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 660.8 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 350.8 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 292.5 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 214.8 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 202.6 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 152.4 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 67.7 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | Nemotron 3 Nano 30B-A3B 30B | NVFP4 | llama.cpp (CUDA) | 67.5 | – | – | – | – | 2026-08 | community | – | source |
| GB10 | nemotron_h_moe 31B.A3.5B | Q4_K - Medium | llama.cpp (Vulkan) | 64.5 | 1661.48 | – | – | tg128 | 2026-01-17 | community | – | source |
| GB10 | nemotron_h_moe 31B.A3.5B | Q4_K - Medium | llama.cpp (CUDA) | 61.76 | 2135.98 | – | – | tg128 | 2026-01-17 | community | – | source |
| GB10 | Ornith-1.5-397B-A17B | IQ2_XXS | llama.cpp (CUDA) | 19.82 | – | – | – | 32768 | 2026-10-02 | community | – | source |
| GB10 | Ornith-1.5-397B-A17B | IQ2_XXS | llama.cpp (CUDA) | 19.18 | – | – | – | 32768 | 2026-10-02 | community | – | source |
| GB10 | Ornith-1.5-397B-A17B | IQ2_XXS | llama.cpp (CUDA) | 19.07 | – | – | – | 32768 | 2026-10-02 | community | – | source |
| GB10 | Ornith-1.5-397B-A17B | IQ2_XXS | llama.cpp (CUDA) | 17.72 | – | – | – | 32768 | 2026-10-02 | community | – | source |
| GB10 | Ornith-1.5-397B-A17B | IQ2_XXS | llama.cpp (CUDA) | 15.00 | – | – | – | 32768 | 2026-10-02 | community | – | source |
| GB10 | Qwen3.6-27B | Q4_K_M | llama.cpp | 26.77 | – | – | – | – | 2026-10-12 | sourced | – | source |
| GB10 | Qwen3.6-27B | Q4_K_M | llama.cpp | 24.29 | – | – | – | – | 2026-10-12 | sourced | – | source |
| GB10 | Qwen3.6-35B-A3B | NVFP4 | vLLM | 118.1 | – | – | – | tg256 | 2026-10-06 | community | – | source |
| GB10 | Qwen3.6-35B-A3B | NVFP4 | vLLM | 72.9 | – | – | – | tg256 | 2026-10-06 | community | – | source |
| GB10 | Qwen3.6-35B-A3B | UD-Q4_K_M | llama.cpp | – | 3271.18 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| GB10 | Qwen3.6-35B-A3B | UD-Q4_K_M | llama.cpp | – | 3406.68 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| GB10 | Qwen3.6-35B-A3B | UD-Q4_K_M | llama.cpp | – | 3254.79 | – | – | 4096 | 2026-10-13 | sourced | – | source |
| GB10 | Qwen3.6-35B-A3B | UD-Q4_K_M | llama.cpp | – | 3366.88 | – | – | 4096 | 2026-10-13 | sourced | – | source |
| GB10 | Qwen3.8-27B | UD-Q8_K_L | llama.cpp | – | 942.84 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| GB10 | Qwen3.8-27B | UD-Q8_K_L | llama.cpp | – | 984.86 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| GB10 | Qwen3.8-27B | UD-Q8_K_L | llama.cpp | – | 928.16 | – | – | 4096 | 2026-10-13 | sourced | – | source |
| GB10 | Qwen3.8-27B | UD-Q8_K_L | llama.cpp | – | 973.34 | – | – | 4096 | 2026-10-13 | sourced | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 73.43 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 72.64 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 67.4 | – | – | – | – | 2026-10-08 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 66.2 | – | – | – | – | 2026-10-08 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 60.9 | – | – | – | – | 2026-10-08 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 58.5 | – | – | – | – | 2026-10-08 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 55.28 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 54.28 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 52.5 | – | – | – | – | 2026-10-08 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 51.8 | – | – | – | – | 2026-10-08 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 51.5 | – | – | – | – | 2026-10-08 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 51.1 | – | – | – | – | 2026-10-08 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 50.5 | – | – | – | tg256 | 2026-10-12 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 49.1 | – | – | – | tg256 | 2026-10-12 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 48.14 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 47.70 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 46.5 | – | – | – | – | 2026-10-04 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 46.32 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 45.92 | – | – | 7.12 | 40960 | 2026-09-10 | sourced | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 44.86 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | UD-IQ4_XS | llama.cpp | 43.97 | – | – | – | – | 2026-10-12 | sourced | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 43.44 | – | – | 6.75 | 40960 | 2026-09-10 | sourced | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 42.84 | – | – | – | – | 2026-10-08 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 42.07 | – | – | – | – | 2026-10-08 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | UD-IQ4_XS | llama.cpp | 41.51 | – | – | – | – | 2026-10-12 | sourced | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 41.06 | – | – | – | – | 2026-10-08 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 40.76 | – | – | – | – | 2026-10-08 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 39.4 | – | – | – | – | 2026-10-04 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 36.31 | – | – | 5.44 | 40960 | 2026-09-10 | sourced | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 34.25 | – | – | 5.09 | 40960 | 2026-09-10 | sourced | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 33.0 | – | – | – | tg256 | 2026-10-12 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 32.6 | – | – | – | tg256 | 2026-10-12 | community | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 32.41 | – | – | 3.4 | 40960 | 2026-09-10 | sourced | – | source |
| GB10 | Qwen3.8-Flash-Next | NVFP4 | vLLM | 23.51 | – | – | 3.45 | 40960 | 2026-09-10 | sourced | – | source |
| GB10 | Qwen3.8-Flash-Next | UD-IQ4_XS | llama.cpp | – | 1044.71 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| GB10 | Qwen3.8-Flash-Next | UD-IQ4_XS | llama.cpp | – | 1104.31 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| GB10 | Qwen3.8-Flash-Next | UD-IQ4_XS | llama.cpp | – | 1068.7 | – | – | 4096 | 2026-10-13 | sourced | – | source |
| GB10 | Qwen3.8-Flash-Next | UD-IQ4_XS | llama.cpp | – | 1124.01 | – | – | 4096 | 2026-10-13 | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085