Run DeepSeek R1 8B on M4

Yes — DeepSeek R1 8B (8B) runs at 78 tok/s on M4 with 16 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.5s. DeepSeek's MIT-licensed 8B reasoning model with chain-of-thought thinking.

Speed

tok/s

First Token

0.5

seconds

RAM Needed

GB minimum

Engine

MLX

recommended

Benchmark Details

LLMCheck measured DeepSeek R1 8B on M4 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	78 tok/s
Time to first token	0.5s
Quantization	Q4_K_M
Minimum RAM	16 GB
Recommended engine	MLX
Parameters	8B
Benchmark date	2026-02

Q4_K_M 8B MLX M4

Setup Guide: Run DeepSeek R1 8B on M4

The recommended engine for DeepSeek R1 8B on M4 is MLX. Install with pip and pull the model:

pip install mlx-lm

mlx_lm.generate --model mlx-community/deepseek-r1-8b-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run deepseek-r1:8b

Performance on Other Apple Silicon Chips

Chip	Speed	First Token	Min RAM	Engine
M5 Max	97 tok/s	0.5s	64 GB	Ollama
M2	58 tok/s	0.8s	16 GB	Ollama
M1	38 tok/s	1.2s	16 GB	Ollama

System Requirements

To run DeepSeek R1 8B on M4 you need:

• Mac with M4 chip (or newer)
• 16 GB unified memory minimum
• macOS 13 Ventura or later
• ~13-16 GB free disk space for the model file
• MLX installed (see our Ollama install guide)

Compare More Models

See how DeepSeek R1 8B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard