Run Qwen 2.5 72B on M5 Max

Yes — Qwen 2.5 72B (72B) runs at 10 tok/s on M5 Max with 128 GB RAM using Q4_K_M quantization via Ollama. First token latency is 3.2s. Alibaba's 72B Qwen 2.5 model — powerful but requires 64 GB+ Mac.

Speed
10
tok/s
First Token
3.2
seconds
RAM Needed
128
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Qwen 2.5 72B 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 second10 tok/s
Time to first token3.2s
QuantizationQ4_K_M
Minimum RAM128 GB
Recommended engineOllama
Parameters72B
Benchmark date2026-03

Q4_K_M 72B Ollama M5 Max

Setup Guide: Run Qwen 2.5 72B on M5 Max

The recommended engine for Qwen 2.5 72B on M5 Max is Ollama. Install Ollama, then pull the model:

ollama run qwen2.5:72b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~128 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M4 Ultra 15 tok/s 2.5s 192 GB Ollama

System Requirements

To run Qwen 2.5 72B on M5 Max you need:

Compare More Models

See how Qwen 2.5 72B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard