Run Qwen 2.5 72B on M4 Ultra

Yes — Qwen 2.5 72B (72B) runs at 15 tok/s on M4 Ultra with 192 GB RAM using Q4_K_M quantization via Ollama. First token latency is 2.5s. Alibaba's 72B Qwen 2.5 model — powerful but requires 64 GB+ Mac.

Speed
15
tok/s
First Token
2.5
seconds
RAM Needed
192
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Qwen 2.5 72B on M4 Ultra 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 second15 tok/s
Time to first token2.5s
QuantizationQ4_K_M
Minimum RAM192 GB
Recommended engineOllama
Parameters72B
Benchmark date2026-02

Q4_K_M 72B Ollama M4 Ultra

Setup Guide: Run Qwen 2.5 72B on M4 Ultra

The recommended engine for Qwen 2.5 72B on M4 Ultra 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 (~192 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 10 tok/s 3.2s 128 GB Ollama

System Requirements

To run Qwen 2.5 72B on M4 Ultra 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