Llama 3.2 1B Instruct on L4
190best gen tok/s
9,573best 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 | 190 | 8,579 | LocalScore ↗ | 512+128 | 174 ms | llamafile 0.9.2 |
| Q4_K - Medium | 189 | 9,573 | LocalScore ↗ | 512+128 | 169 ms | llamafile 0.9.2 |
| Q4_K - Medium | 188 | 9,571 | LocalScore ↗ | 512+128 | 168 ms | llamafile 0.9.2 |
| Q4_K - Medium | 185 | 9,351 | LocalScore ↗ | 512+128 | 172 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.