Hardware /
P106-100
11measured results
78.8best gen tok/s*
6 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 | 78.8 | 1,874 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 78.7 | 1,874 | LocalScore ↗ | 4,352 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 78.7 | 1,879 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 73.9 | 1,812 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 73.9 | 1,823 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 54.8 | 1,525 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 53.3 | 1,520 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 2 7B | Q4_0 | 30.8 | 183 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @23bc779 | Details → |
| Llama 2 7B | Q4_0 | 30.6 | 438 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @5fd160b | Details → |
| Llama 2 7B | Q4_0 | 30.4 | 407 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @5fd160b | Details → |
| Llama 2 7B | Q4_0 | 29.8 | 184 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @23bc779 | 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.