Qwen 3.5 72B

Qwen

Alibaba's flagship 72B model with exceptional multilingual capabilities and strong reasoning. Requires multi-GPU or high VRAM setup.

Provider

Alibaba

Parameters

72B

Context

131.072K

Released

2025-09-01

VRAM Requirements by Quantization

Method	Disk Size	VRAM Required	Fits GPUs
Q4_K_M	41 GB	44 GB	1 GPUs
IQ3_M	30 GB	32 GB	2 GPUs
Q2_K	25 GB	27 GB	3 GPUs

Run in terminal:

ollama pull qwen3.5:72b

Minimum 27GB VRAM required. Install Ollama from ollama.com

mmlu86.3%

humaneval82.7%

Scores are approximate and may vary by quantization level.

HuggingFace

Qwen/Qwen3.5-72B-Instruct