Apple M3 Pro (14-core GPU) × Meta Llama 3.1 8B Instruct
Meta Llama 3.1 8B Instruct on Apple M3 Pro (14-core GPU)
22.2best gen tok/s
230best 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 | 22.2 | 230 | LocalScore ↗ | 4,352 | 5,553 ms | llamafile 0.9.2 |
| Q4_K - Medium | 22.0 | 224 | LocalScore ↗ | 512+128 | 5,638 ms | llamafile 0.9.2 |
| Q4_K - Medium | 21.5 | 223 | LocalScore ↗ | 512+128 | 5,652 ms | llamafile 0.9.2 |
| Q4_K - Medium | 19.1 | 200 | LocalScore ↗ | 512+128 | 6,428 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 M3 Pro (14-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.