Run Qwen 3 32B on M5 Max

Yes — Qwen 3 32B (32B) runs at 28 tok/s on M5 Max with 128 GB RAM using Q4_K_M quantization via Ollama. First token latency is 1.1s. Alibaba's 32B dense model for Macs with 32 GB+ RAM.

Speed
28
tok/s
First Token
1.1
seconds
RAM Needed
128
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Qwen 3 32B on M5 Max 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 second28 tok/s
Time to first token1.1s
QuantizationQ4_K_M
Minimum RAM128 GB
Recommended engineOllama
Parameters32B
Benchmark date2026-03

Q4_K_M 32B Ollama M5 Max

Setup Guide: Run Qwen 3 32B on M5 Max

The recommended engine for Qwen 3 32B on M5 Max is Ollama. Install Ollama, then pull the model:

ollama run qwen3:32b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~128 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
M4 Max 22 tok/s 1.4s 64 GB MLX
M4 Pro 15 tok/s 1.8s 32 GB Ollama

System Requirements

To run Qwen 3 32B on M5 Max 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