Apple M5 (10-core GPU) × Meta Llama 3.1 8B Instruct
Meta Llama 3.1 8B Instruct on Apple M5 (10-core GPU)
22.4best gen tok/s
211best 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 | 22.4 | 211 | LocalScore ↗ | 512+128 | 5,984 ms | llamafile 0.9.2 |
| Q4_K - Medium | 22.3 | 211 | LocalScore ↗ | 512+128 | 5,987 ms | llamafile 0.9.2 |
| Q4_K - Medium | 22.2 | 210 | LocalScore ↗ | 512+128 | 6,022 ms | llamafile 0.9.2 |
| Q4_K - Medium | 19.6 | 177 | LocalScore ↗ | 4,352 | 6,615 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 M5 (10-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.