RTX 4080 × Qwen2.5 14B Instruct
Qwen2.5 14B Instruct on RTX 4080
52.1best gen tok/s
2,778best prompt tok/s
640max context tested
5results
Measured · all numbers below come from the linked sources
llama.cpp
| Quant | Gen tok/s | Prompt tok/s | Source | Context tested | TTFT | Build |
|---|---|---|---|---|---|---|
| Q4_K - Medium | 52.1 | 2,665 | LocalScore ↗ | 512+128 | 488 ms | llamafile 0.9.2 |
| Q4_K - Medium | 48.9 | 2,778 | LocalScore ↗ | 512+128 | 478 ms | llamafile 0.9.3 |
| Q4_K - Medium | 48.2 | 2,747 | LocalScore ↗ | 512+128 | 482 ms | llamafile 0.9.3 |
| Q4_K - Medium | 13.5 | 1,747 | LocalScore ↗ | 512+128 | 768 ms | llamafile 0.9.3 |
| Q4_K - Medium | 13.4 | 1,760 | LocalScore ↗ | 512+128 | 756 ms | llamafile 0.9.3 |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →
"Context tested" is the largest prompt+generation length actually benchmarked (tokens), not a memory-fit estimate.
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.