Run Qwen 3.5 9B on M5 Max

Yes — Qwen 3.5 9B (9B) runs at 105 tok/s on M5 Max with 64 GB RAM using Q4_K_M quantization via Ollama. First token latency is 0.5s. Alibaba's 9B model — top pick for 8 GB and 16 GB Macs.

Speed
105
tok/s
First Token
0.5
seconds
RAM Needed
64
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Qwen 3.5 9B 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 second105 tok/s
Time to first token0.5s
QuantizationQ4_K_M
Minimum RAM64 GB
Recommended engineOllama
Parameters9B
Benchmark date2026-03

Q4_K_M 9B Ollama M5 Max

Setup Guide: Run Qwen 3.5 9B on M5 Max

The recommended engine for Qwen 3.5 9B on M5 Max is Ollama. Install Ollama, then pull the model:

ollama run qwen3.5:9b

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 Pro 92 tok/s 0.4s 24 GB MLX
M4 72 tok/s 0.6s 16 GB LM Studio
M3 58 tok/s 0.7s 16 GB Ollama
M1 35 tok/s 1.1s 16 GB Ollama

System Requirements

To run Qwen 3.5 9B on M5 Max you need:

Compare More Models

See how Qwen 3.5 9B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard