Run Qwen 3 32B on M4 Max

Yes — Qwen 3 32B (32B) runs at 22 tok/s on M4 Max with 64 GB RAM using Q4_K_M quantization via MLX. First token latency is 1.4s. Alibaba's 32B dense model for Macs with 32 GB+ RAM.

Speed

tok/s

First Token

1.4

seconds

RAM Needed

GB minimum

Engine

MLX

recommended

Benchmark Details

LLMCheck measured Qwen 3 32B on M4 Max 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	22 tok/s
Time to first token	1.4s
Quantization	Q4_K_M
Minimum RAM	64 GB
Recommended engine	MLX
Parameters	32B
Benchmark date	2026-02

Q4_K_M 32B MLX M4 Max

Setup Guide: Run Qwen 3 32B on M4 Max

The recommended engine for Qwen 3 32B on M4 Max is MLX. Install with pip and pull the model:

pip install mlx-lm

mlx_lm.generate --model mlx-community/qwen-3-32b-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run qwen3:32b

Performance on Other Apple Silicon Chips

Chip	Speed	First Token	Min RAM	Engine
M4 Ultra	32 tok/s	1.0s	192 GB	Ollama
M5 Max	28 tok/s	1.1s	128 GB	Ollama
M4 Pro	15 tok/s	1.8s	32 GB	Ollama

System Requirements

To run Qwen 3 32B on M4 Max you need:

• Mac with M4 Max chip (or newer)
• 64 GB unified memory minimum
• macOS 13 Ventura or later
• ~54-64 GB free disk space for the model file
• MLX installed (see our Ollama install guide)

Compare More Models

See how Qwen 3 32B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard