DeepSeekDeepSeek V3 on Apple M4 Ultra (192GB)
M4 Ultra (192GB) runs DeepSeek V3 at Q2_K — 5 tok/s due to limited memory bandwidth. Slow but functional — see all options below.
Model Size
671B
Device VRAM
192 GB
Bandwidth
819 GB/s
Quantization
Q2_K
Performance by Quantization
OwnRig currently has one published compatibility entry for DeepSeek V3 on Apple M4 Ultra (192GB) at Q2_K. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q2_K | 5 tok/s | 3333ms | ✓ Yes | Marginal | estimated |
Notes
Q2_K
M4 Ultra: ~1.5x M4 Max performance due to higher memory bandwidth and GPU cores.
About DeepSeek V3
DeepSeek V3 (671B) is a chat, coding, ai coding, reasoning, multi-purpose model. Massive MoE model rivaling GPT-4 class. Only ~37B parameters active per token despite 671B total. Requires multi-GPU or very large unified memory (128GB+ Apple Silicon at Q2/Q3). Not for casual home use. Included for completeness and to show what the high end looks like.
View all DeepSeek V3 hardware options →About Apple M4 Ultra (192GB)
Apple M4 Ultra (192GB) has 192 GB at 819 GB/s. Available in Mac Studio, Mac Pro.
See all models Apple M4 Ultra (192GB) can run →Estimate method: Estimated from M4 Max benchmarks scaled by memory bandwidth ratio (819/546 GB/s). Reference hardware source: github.com (2026-03-14)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.