Apple M2 Ultra (60-core GPU) × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on Apple M2 Ultra (60-core GPU)
176best gen tok/s
3,296best 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 | 176 | 3,296 | LocalScore ↗ | 512+128 | 334 ms | llamafile 0.9.2 |
| Q4_K - Medium | 174 | 3,290 | LocalScore ↗ | 512+128 | 335 ms | llamafile 0.9.2 |
| Q4_K - Medium | 170 | 3,272 | LocalScore ↗ | 512+128 | 339 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 M2 Ultra (60-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.