Models /
DeepSeek R1 Distill Llama 8B
4results
3devices
8.03Bparams
68.3fastest gen tok/s
llama.cpp
| Hardware | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| RTX 2080 Ti | Q4_K - Medium | 68.3 | 2,034 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| RTX 3070 | Q6_K | 52.8 | 2,027 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| RTX 3070 | Q6_K | 52.8 | 2,039 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| RTX 3050 | Q4_K - Medium | 26.0 | 813 | 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.