Hardware /
Tesla P40
10measured results
118best gen tok/s*
24 GBreported memory
*Headline excludes tiny/test models (under 0.6B params or TinyStories-style). Open in rig checker →
llama.cpp
| Model | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | Q4_K - Medium | 118 | 2,965 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 63.4 | 1,452 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 2 7B | Q4_0 | 59.4 | 488 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @N/A | Details → |
| Llama 2 7B | Q4_0 | 59.2 | 484 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @N/A | Details → |
| Llama 2 7B | Q4_0 | 54.7 | 1,007 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @c76b420 | Details → |
| Llama 2 7B | Q4_0 | 53.7 | 1,080 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @c76b420 | Details → |
| LLaMA v2 | Q4_0 | 40.9 | 833 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen3-Coder-30B-A3B-Instruct-1M | Q4_K - Medium | 29.3 | 288 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 15.7 | 339 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 11.5 | 245 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →
Includes results from LocalScore, a Mozilla Builders project by cjpais, mirrored in the cn0303/local-llm-speed-benchmarks dataset. LocalScore runs use llamafile, which is built on llama.cpp.