Run Qwen 3.5 35B on M4 Max

Yes — Qwen 3.5 35B (35B) runs at 34 tok/s on M4 Max with 48 GB RAM using Q4_K_M quantization via Ollama. First token latency is 1.2s. Alibaba's 35B dense model for high-RAM Macs needing top-tier output.

Speed
34
tok/s
First Token
1.2
seconds
RAM Needed
48
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Qwen 3.5 35B on M4 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 second34 tok/s
Time to first token1.2s
QuantizationQ4_K_M
Minimum RAM48 GB
Recommended engineOllama
Parameters35B
Benchmark date2026-02

Q4_K_M 35B Ollama M4 Max

Setup Guide: Run Qwen 3.5 35B on M4 Max

The recommended engine for Qwen 3.5 35B on M4 Max is Ollama. Install Ollama, then pull the model:

ollama run qwen3.5:35b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~48 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 52 tok/s 0.9s 64 GB MLX
M5 Max 48 tok/s 0.9s 128 GB Ollama
M3 Max 22 tok/s 1.5s 96 GB Ollama

System Requirements

To run Qwen 3.5 35B on M4 Max you need:

Compare More Models

See how Qwen 3.5 35B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard