M3 Ultra 512GB does 18 t/s with DeepSeek R1 671B Q4
gpu4.pics
via AliNT77
Apple M3 Ultra
1× Apple M3 Ultra (512GB unified memory) · 512 GB total VRAM · Apple M3 Ultra
512 GB unified Apple
running DeepSeek R1 671B· Q4
18
tokens / sec
Generation
18tok/s
higher is better
Prompt / prefill
—tok/s
higher is better
Time to first token
—
lower is better
Composite score
—
Model size
671B
Runtime
—
All benchmarks on this rig
| Model | Quant | Gen | Prompt | TTFT | Power | Perf/W | $/Mtok | Score |
|---|---|---|---|---|---|---|---|---|
| DeepSeek R1 671B | Q4 | 18 | — | — | — | — | — | — |