Yes — DeepSeek R2 (671B) runs at 12 tok/s on M4 Ultra with 192 GB RAM using Q3_K_M quantization via MLX. First token latency is 2.0s. A capable open-source LLM with 671B parameters.
Want to run DeepSeek R2 faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates DeepSeek R2 on M4 Ultra using our published methodology: Q4_K_M quantization, memory-bandwidth scaling, and cross-referenced third-party benchmarks where available. Figures are transparent estimates — own this config? Submit a real benchmark →
| Metric | Value |
|---|---|
| Tokens per second | 12 tok/s |
| Time to first token | 2.0s |
| Quantization | Q3_K_M |
| Minimum RAM | 192 GB |
| Recommended engine | MLX |
| Parameters | 671B |
| Benchmark date | 2026-05 |
Q3_K_M 671B MLX M4 Ultra
The recommended engine for DeepSeek R2 on M4 Ultra is MLX. Install with pip and pull the model:
Alternatively, you can use Ollama for a simpler setup:
To run DeepSeek R2 on M4 Ultra you need:
DeepSeek R2 needs about 192 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep our benchmarks free.
See how DeepSeek R2 stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard