Run Qwen 3 32B on M4 Pro

Yes — Qwen 3 32B (32B) runs at 15 tok/s on M4 Pro with 32 GB RAM using Q4_K_M quantization via Ollama. First token latency is 1.8s. Alibaba's 32B dense model for Macs with 32 GB+ RAM.

Speed
15
tok/s
First Token
1.8
seconds
RAM Needed
32
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Qwen 3 32B on M4 Pro using the standard methodology: Q4_K_M quantization, 256-token input, 512-token output, 3 runs averaged on a freshly-booted system.

MetricValue
Tokens per second15 tok/s
Time to first token1.8s
QuantizationQ4_K_M
Minimum RAM32 GB
Recommended engineOllama
Parameters32B
Benchmark date2026-01

Q4_K_M 32B Ollama M4 Pro

Setup Guide: Run Qwen 3 32B on M4 Pro

The recommended engine for Qwen 3 32B on M4 Pro is Ollama. Install Ollama, then pull the model:

ollama run qwen3:32b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~32 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M4 Ultra 32 tok/s 1.0s 192 GB Ollama
M5 Max 28 tok/s 1.1s 128 GB Ollama
M4 Max 22 tok/s 1.4s 64 GB MLX

System Requirements

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

Compare More Models

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

Open Compare Tool Full Leaderboard