Local LLM model page

Qwen 2.5 VL (72B)

Qwen massive vision-language model. Exceptional image and video understanding at 72B scale. 72K context.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
72B
Minimum RAM
64 GB
Model size
42 GB
Quantization
Q4_K_M

Can Qwen 2.5 VL (72B) run locally?

Qwen 2.5 VL (72B) is best suited for high-end workstations with 64 GB RAM. LocalClaw recommends Q4_K_M as the default quantization, with at least 64 GB RAM.

Search term for LM Studio or compatible runtimes: qwen2.5-vl-72b-instruct

Hugging Face repository: Qwen/Qwen2.5-VL-72B-Instruct-GGUF

visionquality

Strengths

  • Qwen massive vision-language model. Exceptional image and video understanding at 72B scale. 72K context.

Limitations

  • Performance depends heavily on quantization, RAM bandwidth and runtime support.

Best use cases

  • vision
  • quality

Benchmarks

Speed: 2/10

Quality: 10/10

Coding: 7/10

Reasoning: 9/10

Technical details

Developer: qwen

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2025-01