Apple M3 Ultra (80-core GPU) × Meta Llama 3.1 8B Instruct
Meta Llama 3.1 8B Instruct on Apple M3 Ultra (80-core GPU)
63.3best gen tok/s
1,119best prompt tok/s
640max context tested
3results
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 | 63.3 | 1,062 | LocalScore ↗ | 512+128 | 1,102 ms | llamafile 0.9.2 |
| Q4_K - Medium | 62.7 | 1,119 | LocalScore ↗ | 512+128 | 1,055 ms | llamafile 0.9.2 |
| Q4_K - Medium | 62.6 | 1,100 | LocalScore ↗ | 512+128 | 1,066 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 Ultra (80-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.