Hardware /
GTX 1080 Ti
19measured results
153best gen tok/s*
11 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 | 153 | 4,259 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 146 | 4,068 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 146 | 4,075 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 145 | 4,042 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 144 | 4,047 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Gemma 3 1b It | Q4_K - Medium | 129 | 5,556 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Gemma 3 1b It | Q4_K - Medium | 128 | 5,367 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 2 7B | Q4_0 | 65.0 | 541 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @360d653 | Details → |
| Llama 2 7B | Q4_0 | 64.6 | 530 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @360d653 | Details → |
| Llama 2 7B | Q4_0 | 62.5 | 1,084 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @9c35706 | Details → |
| Llama 2 7B | Q4_0 | 61.4 | 1,138 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @9c35706 | Details → |
| Gemma 3 4b It | Q4_K - Medium | 57.4 | 1,689 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Gemma 3 4b It | Q4_K - Medium | 57.3 | 1,628 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 21.1 | 449 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 20.6 | 427 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 20.2 | 424 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| DeepSeek R1 Distill Qwen 14B | Q4_K - Medium | 20.1 | 442 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 19.6 | 412 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 19.4 | 381 | 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.