Apple M1 Pro (16-core GPU) × Meta Llama 3.1 8B Instruct
Meta Llama 3.1 8B Instruct on Apple M1 Pro (16-core GPU)
22.7best gen tok/s
207best prompt tok/s
640max context tested
6results
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 | 22.7 | 207 | LocalScore ↗ | 512+128 | 6,043 ms | llamafile 0.9.2 |
| Q4_K - Medium | 22.0 | 205 | LocalScore ↗ | 512+128 | 6,094 ms | llamafile 0.9.2 |
| Q4_K - Medium | 22.0 | 205 | LocalScore ↗ | 512+128 | 6,087 ms | llamafile 0.9.2 |
| Q4_K - Medium | 21.9 | 202 | LocalScore ↗ | 512+128 | 6,178 ms | llamafile 0.9.2 |
| Q4_K - Medium | 21.2 | 195 | LocalScore ↗ | 512+128 | 6,409 ms | llamafile 0.9.2 |
| Q4_K - Medium | 21.0 | 202 | LocalScore ↗ | 512+128 | 6,140 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.
What else can Apple M1 Pro (16-core GPU) run? →
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.