Apple M4 Max (32-core GPU) × DeepSeek R1 Distill Qwen 14B
DeepSeek R1 Distill Qwen 14B on Apple M4 Max (32-core GPU)
27.8best gen tok/s
293best prompt tok/s
640max context tested
1results
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 - Small | 27.8 | 293 | LocalScore ↗ | 512+128 | 4,333 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 M4 Max (32-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.