Run Qwen 3 4B on M4 Pro

Yes — Qwen 3 4B (4B) runs at 118 tok/s on M4 Pro with 24 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.3s. Alibaba's 4B dense model with strong multilingual and coding capabilities.

Speed
118
tok/s
First Token
0.3
seconds
RAM Needed
24
GB minimum
Engine
MLX
recommended
Want to run Qwen 3 4B faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates Qwen 3 4B on M4 Pro using our published methodology: Q4_K_M quantization, memory-bandwidth scaling, and cross-referenced third-party benchmarks where available. Figures are transparent estimates — own this config? Submit a real benchmark →

MetricValue
Tokens per second118 tok/s
Time to first token0.3s
QuantizationQ4_K_M
Minimum RAM24 GB
Recommended engineMLX
Parameters4B
Benchmark date2026-02

Q4_K_M 4B MLX M4 Pro

Setup Guide: Run Qwen 3 4B on M4 Pro

The recommended engine for Qwen 3 4B on M4 Pro is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/qwen-3-4b-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run qwen3:4b

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 135 tok/s 0.2s 64 GB Ollama
M2 52 tok/s 0.7s 8 GB Ollama

System Requirements

To run Qwen 3 4B on M4 Pro you need:

🛒 Get a Mac that runs Qwen 3 4B

Qwen 3 4B needs about 24 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep our benchmarks free.

Compare More Models

See how Qwen 3 4B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard