Run DeepSeek R2 on M4 Ultra

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.

Speed
12
tok/s
First Token
2.0
seconds
RAM Needed
192
GB minimum
Engine
MLX
recommended
Want to run DeepSeek R2 faster — or step up to bigger models? Find your Mac →

Benchmark Details

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 →

MetricValue
Tokens per second12 tok/s
Time to first token2.0s
QuantizationQ3_K_M
Minimum RAM192 GB
Recommended engineMLX
Parameters671B
Benchmark date2026-05

Q3_K_M 671B MLX M4 Ultra

Setup Guide: Run DeepSeek R2 on M4 Ultra

The recommended engine for DeepSeek R2 on M4 Ultra is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/deepseek-r2-q3_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run deepseek-r2

System Requirements

To run DeepSeek R2 on M4 Ultra you need:

🛒 Get a Mac that runs DeepSeek R2

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.

Compare More Models

See how DeepSeek R2 stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard