RTX 5090 × Meta Llama 3.1 8B Instruct
Meta Llama 3.1 8B Instruct on RTX 5090
106best gen tok/s
8,441best 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 | 106 | 8,441 | LocalScore ↗ | 512+128 | 161 ms | llamafile 0.9.2 |
| Q4_K - Medium | 70.0 | 5,758 | LocalScore ↗ | 4,352 | 415 ms | llamafile 0.9.2 |
| Q4_K - Medium | 45.8 | 4,682 | LocalScore ↗ | 512+128 | 282 ms | llamafile 0.9.2 |
| Q4_K - Medium | 43.2 | 6,307 | LocalScore ↗ | 512+128 | 207 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.