Models /
Qwen2.5.1 Coder 7B Instruct
4results
3devices
7.62Bparams
68.0fastest gen tok/s
llama.cpp
| Hardware | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| RTX 2080 Ti | Q4_K - Medium | 68.0 | 2,355 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| RTX 2080 Ti | Q6_K | 57.1 | 2,136 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| AMD Radeon RX 6650 XT | Q4_K - Medium | 26.8 | 566 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| AMD Radeon RX 6600 XT | Q6_K | 23.1 | 507 | LocalScore ↗ | 4,352 | 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.