Llama 3.2 1B Instruct on H200
99.0best gen tok/s
15,261best prompt tok/s
640max 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 | 99.0 | 15,261 | LocalScore ↗ | 512+128 | 84 ms | llamafile 0.9.2 |
| Q4_K - Medium | 98.7 | 15,044 | LocalScore ↗ | 512+128 | 86 ms | llamafile 0.9.2 |
| Q4_K - Medium | 98.5 | 14,963 | LocalScore ↗ | 512+128 | 86 ms | llamafile 0.9.2 |
| Q4_K - Medium | 97.8 | 13,517 | LocalScore ↗ | 512+128 | 98 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.