Models /
Qwen1.5-0.5B-Chat-AWQ-fp16
2results
2devices
0.62Bparams
172fastest gen tok/s
llama.cpp
| Hardware | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| RTX 5070 Ti | Q4_K - Medium | 172 | 16,250 | LocalScore ↗ | 4,352 | llamafile 0.9.3 | Details → |
| GTX 1660 SUPER | Q8_0 | 63.1 | 1,795 | 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.