Run Qwen 3 30B-A3B on M5 Max

Yes — Qwen 3 30B-A3B (30B) runs at 62 tok/s on M5 Max with 64 GB RAM using Q4_K_M quantization via Ollama. First token latency is 0.7s. Alibaba's 30B MoE activating 3B params — large-model quality at mid-RAM cost.

Speed
62
tok/s
First Token
0.7
seconds
RAM Needed
64
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Qwen 3 30B-A3B 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 second62 tok/s
Time to first token0.7s
QuantizationQ4_K_M
Minimum RAM64 GB
Recommended engineOllama
Parameters30B
Benchmark date2026-03

Q4_K_M 30B Ollama M5 Max

Setup Guide: Run Qwen 3 30B-A3B on M5 Max

The recommended engine for Qwen 3 30B-A3B on M5 Max is Ollama. Install Ollama, then pull the model:

ollama run qwen3:30b-a3b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~64 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M4 Max 42 tok/s 0.9s 48 GB Ollama
M4 Pro 35 tok/s 1.0s 24 GB MLX
M3 Max 28 tok/s 1.3s 36 GB Ollama

System Requirements

To run Qwen 3 30B-A3B on M5 Max 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