Models /
DeepSeek R1 Distill Qwen 7B
4results
4devices
7.62Bparams
54.2fastest gen tok/s
llama.cpp
| Hardware | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| RTX 2080 Ti | Q6_K | 54.2 | 1,459 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Apple M4 Max (32-core GPU) | Q4_K - Medium | 51.9 | 598 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| RTX 3050 | Q4_K - Medium | 27.3 | 911 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| GTX 1060 6GB | Q4_K - Medium | 19.1 | 365 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | 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.