Run Qwen 3.5 4B on M4

Yes — Qwen 3.5 4B (4B) runs at 92 tok/s on M4 with 16 GB RAM using Q4_K_M quantization via Ollama. First token latency is 0.4s. Alibaba's compact 4B model offering excellent quality-per-token for its size.

Speed
92
tok/s
First Token
0.4
seconds
RAM Needed
16
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Qwen 3.5 4B on M4 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 second92 tok/s
Time to first token0.4s
QuantizationQ4_K_M
Minimum RAM16 GB
Recommended engineOllama
Parameters4B
Benchmark date2026-02

Q4_K_M 4B Ollama M4

Setup Guide: Run Qwen 3.5 4B on M4

The recommended engine for Qwen 3.5 4B on M4 is Ollama. Install Ollama, then pull the model:

ollama run qwen3.5:4b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~16 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 148 tok/s 0.2s 64 GB MLX

System Requirements

To run Qwen 3.5 4B on M4 you need:

Compare More Models

See how Qwen 3.5 4B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard