Run Qwen 4 4B on M1

Yes — Qwen 4 4B (4B) runs at 45 tok/s on M1 with 8 GB RAM using Q4_K_M quantization via Ollama. First token latency is 0.6s. A capable open-source LLM with 4B parameters.

Speed
45
tok/s
First Token
0.6
seconds
RAM Needed
8
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Qwen 4 4B on M1 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 second45 tok/s
Time to first token0.6s
QuantizationQ4_K_M
Minimum RAM8 GB
Recommended engineOllama
Parameters4B
Benchmark date2026-06

Q4_K_M 4B Ollama M1

Setup Guide: Run Qwen 4 4B on M1

The recommended engine for Qwen 4 4B on M1 is Ollama. Install Ollama, then pull the model:

ollama run qwen-4-4b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~8 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 135 tok/s 0.2s 128 GB MLX
M4 Pro 108 tok/s 0.3s 24 GB Ollama
M3 85 tok/s 0.3s 16 GB MLX
M2 62 tok/s 0.4s 8 GB Ollama

System Requirements

To run Qwen 4 4B on M1 you need:

Compare More Models

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

Open Compare Tool Full Leaderboard