Models /
Qwen2.5 1.5B Instruct
3results
1devices
1.78Bparams
207fastest gen tok/s
llama.cpp
| Hardware | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| RTX 3090 | Q6_K | 207 | 11,291 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| RTX 3090 | Q6_K | 205 | 11,146 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| RTX 3090 | Q6_K | 204 | 11,246 | 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.