RTX 5070 × Qwen2.5 14B Instruct
Qwen2.5 14B Instruct on RTX 5070
45.7best gen tok/s
1,758best prompt tok/s
4,352max context tested
2results
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 | 45.7 | 1,758 | LocalScore ↗ | 4,352 | 1,195 ms | llamafile 0.9.2 |
| Q4_K - Medium | 20.8 | 1,264 | LocalScore ↗ | 512+128 | 1,075 ms | llamafile 0.9.2 |
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.