Written by Jakub Rusinowski · Last updated January 25, 2025
Alibaba's powerful vision-language models that understand images, documents, charts, and videos alongside text. Qwen 2.5 VL 72B rivals GPT-4V on multiple visual benchmarks, while the 7B version delivers strong OCR and document parsing in under 6GB VRAM.
| Licence | What it permits | Applies to |
|---|---|---|
Apache-2.0 | Commercial use permitted Commercial use permitted. No usage restrictions beyond attribution. | Qwen 2.5 VL 7B Instruct, Qwen 2.5 VL 72B Instruct |
| Qwen 2.5 VL 7B Instruct | Min 6 GB VRAM · Q4_K_M · 128,000 ctx · ollama run qwen2.5vl:7b |
| Qwen 2.5 VL 72B Instruct | Min 45 GB VRAM · Q4_K_M · 128,000 ctx · ollama run qwen2.5vl:72b |
The cheapest GPU that runs Qwen 2.5 VL locally (min 6 GB VRAM) is the Intel Arc B570 (10 GB).
Install Ollama then run: ollama run qwen2.5vl:7b
Minimum VRAM: 6 GB. For best results use Q4_K_M quantization.
Qwen 2.5 VL needs about 6 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Qwen 2.5 VL 7B Instruct (6 GB, Q4_K_M); Qwen 2.5 VL 72B Instruct (45 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — Qwen 2.5 VL runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
Q4_K_M is the best balance of quality and VRAM for Qwen 2.5 VL in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Install Ollama, then run: ollama run qwen2.5vl:7b. This downloads Qwen 2.5 VL and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.