Run DeepSeek R1 70B on M4 Ultra

Yes — DeepSeek R1 70B (70B) runs at 16 tok/s on M4 Ultra with 192 GB RAM using Q4_K_M quantization via MLX. First token latency is 2.2s. DeepSeek's full 70B reasoning distillation — requires 64 GB+ Mac.

Speed

tok/s

First Token

2.2

seconds

RAM Needed

192

GB minimum

Engine

MLX

recommended

Benchmark Details

LLMCheck measured DeepSeek R1 70B on M4 Ultra using the standard methodology: Q4_K_M quantization, 256-token input, 512-token output, 3 runs averaged on a freshly-booted system.

Metric	Value
Tokens per second	16 tok/s
Time to first token	2.2s
Quantization	Q4_K_M
Minimum RAM	192 GB
Recommended engine	MLX
Parameters	70B
Benchmark date	2026-02

Q4_K_M 70B MLX M4 Ultra

Setup Guide: Run DeepSeek R1 70B on M4 Ultra

The recommended engine for DeepSeek R1 70B on M4 Ultra is MLX. Install with pip and pull the model:

pip install mlx-lm

mlx_lm.generate --model mlx-community/deepseek-r1-70b-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run deepseek-r1:70b

Performance on Other Apple Silicon Chips

Chip	Speed	First Token	Min RAM	Engine
M5 Max	11 tok/s	3.0s	128 GB	Ollama

System Requirements

To run DeepSeek R1 70B on M4 Ultra you need:

• Mac with M4 Ultra chip (or newer)
• 192 GB unified memory minimum
• macOS 13 Ventura or later
• ~163-192 GB free disk space for the model file
• MLX installed (see our Ollama install guide)

Compare More Models

See how DeepSeek R1 70B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard