# QwenLM/Qwen-VL

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

Repository: https://github.com/QwenLM/Qwen-VL
Canonical: https://ross.abutalabs.com/products/qwen-vl
Language: Python
License: NOASSERTION
License Family: other
Topics: large-language-models, vision-language-model
Last push: 2024-08-07T02:37:06+00:00

## Health v2 (maintenance only)
Score: 28/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 79
- inputs: {"age_days": 1108, "days_push": 757, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6726, forks 495 (observed 2026-08-28T04:09:48.100512+00:00)

## What it is
Official repository for Qwen-VL, Alibaba Cloud's large vision-language model family, including the pretrained Qwen-VL and instruction-tuned Qwen-VL-Chat checkpoints with quantized variants. It provides model weights, inference code, fine-tuning support, and demos for multimodal image understanding and visual question answering.

## Use cases
- run a vision-language model to answer questions about images
- perform OCR and text recognition on images with an LLM
- build a multimodal chatbot that understands images
- fine-tune a vision-language model on custom data
- compare visual reasoning capabilities of open VLMs
- deploy a quantized multimodal model locally

## When to choose
- you need an open-weights vision-language model for image understanding
- you want multimodal chat with strong OCR and high-resolution image support
- you need a VLM you can fine-tune or quantize for local deployment

## When to avoid
- you only need text-only LLM capabilities
- you want a hosted API without managing model weights
- you need video or audio multimodality rather than images

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, llm-inference, computer-vision, ocr, chatbot
- domain: large-language-models, computer-vision, artificial-intelligence
- platform: python, cross-platform
- tags: vision-language-model, multimodal, qwen, alibaba-cloud, image-understanding, pretrained-model, chat-model, natural-language-processing, gpu, linux

## Member repositories
- QwenLM/Qwen-VL (main) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:48.100512+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:42:53.722768+00:00, confidence not recorded.
  - readme: https://github.com/QwenLM/Qwen-VL (fetched 2026-08-28T04:09:48.100512+00:00, sha 8ddf838bd769)
- Data as of 2026-08-30T08:39:29.467469+00:00.