RTX 3050 × Meta Llama 3.1 8B Instruct
Meta Llama 3.1 8B Instruct on RTX 3050
35.0best gen tok/s
979best prompt tok/s
4,352max context tested
4results
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 | 35.0 | 965 | LocalScore ↗ | 4,352 | 1,363 ms | llamafile 0.9.3 |
| Q4_K - Medium | 34.5 | 979 | LocalScore ↗ | 512+128 | 1,328 ms | llamafile 0.9.2 |
| Q4_K - Medium | 26.0 | 760 | LocalScore ↗ | 512+128 | 2,315 ms | llamafile 0.9.2 |
| Q4_K - Medium | 25.8 | 797 | LocalScore ↗ | 4,352 | 1,662 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.