RTX 3070 × Meta Llama 3.1 8B Instruct
Meta Llama 3.1 8B Instruct on RTX 3070
66.1best gen tok/s
2,204best prompt tok/s
640max context tested
9results
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 | 66.1 | 2,204 | LocalScore ↗ | 512+128 | 599 ms | llamafile 0.9.2 |
| Q4_K - Medium | 65.9 | 2,150 | LocalScore ↗ | 512+128 | 605 ms | llamafile 0.9.2 |
| Q4_K - Medium | 64.7 | 1,468 | LocalScore ↗ | 512+128 | 1,405 ms | llamafile 0.9.2 |
| Q4_K - Medium | 63.4 | 2,184 | LocalScore ↗ | 512+128 | 595 ms | llamafile 0.9.2 |
| Q4_K - Medium | 62.7 | 2,198 | LocalScore ↗ | 512+128 | 600 ms | llamafile 0.9.3 |
| Q4_K - Medium | 60.5 | 2,160 | LocalScore ↗ | 512+128 | 611 ms | llamafile 0.9.2 |
| Q4_K - Medium | 60.3 | 2,145 | LocalScore ↗ | 512+128 | 609 ms | llamafile 0.9.2 |
| Q4_K - Medium | 59.7 | 1,745 | LocalScore ↗ | 512+128 | 696 ms | llamafile 0.9.3 |
| Q4_K - Medium | 36.4 | 1,821 | LocalScore ↗ | 512+128 | 694 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.