Run Qwen 3 30B-A3B on M4 Pro

Yes — Qwen 3 30B-A3B (30B) runs at 35 tok/s on M4 Pro with 24 GB RAM using Q4_K_M quantization via MLX. First token latency is 1.0s. Alibaba's 30B MoE activating 3B params — large-model quality at mid-RAM cost.

Speed
35
tok/s
First Token
1.0
seconds
RAM Needed
24
GB minimum
Engine
MLX
recommended

Benchmark Details

LLMCheck measured Qwen 3 30B-A3B 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 second35 tok/s
Time to first token1.0s
QuantizationQ4_K_M
Minimum RAM24 GB
Recommended engineMLX
Parameters30B
Benchmark date2026-02

Q4_K_M 30B MLX M4 Pro

Setup Guide: Run Qwen 3 30B-A3B on M4 Pro

The recommended engine for Qwen 3 30B-A3B on M4 Pro is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/qwen-3-30b-a3b-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run qwen3:30b-a3b

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 62 tok/s 0.7s 64 GB Ollama
M4 Max 42 tok/s 0.9s 48 GB Ollama
M3 Max 28 tok/s 1.3s 36 GB Ollama

System Requirements

To run Qwen 3 30B-A3B on M4 Pro you need:

Compare More Models

See how Qwen 3 30B-A3B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard