# zai-org/GLM-V

GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Repository: https://github.com/zai-org/GLM-V
Canonical: https://ross.abutalabs.com/products/glm-v
Language: Python
License: Apache-2.0
License Family: permissive
Topics: image2text, video-understanding, vlm, reasoning
Last push: 2026-07-21T16:03:29+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 35, longevity 30
- inputs: {"age_days": 431, "days_push": 43, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2370, forks 180 (observed 2026-08-28T04:06:41.777966+00:00)

## What it is
GLM-V is the open-source repository for Zhipu AI's GLM-4.6V, GLM-4.5V, and GLM-4.1V-Thinking vision-language models, which perform versatile multimodal reasoning trained with scalable reinforcement learning. It provides model weights, inference examples, a VLM reward system, and companion projects like a desktop assistant app and UI2Code.

## Use cases
- run a vision-language model to caption and answer questions about images
- understand and reason over video content
- build multimodal AI agents that see screenshots and documents
- convert UI screenshots to code
- fine-tune or evaluate VLMs with a reinforcement learning reward system
- build a desktop assistant that reads the screen via screenshots

## When to choose
- you need open-weights multimodal reasoning models for image or video understanding
- you want strong VLM performance with Apache-2.0 licensing for commercial use
- you need grounding, OCR-like extraction, or UI-to-code capabilities from a VLM
- you want to experiment with RL-trained vision-language reasoning

## When to avoid
- you only need text-only LLMs without vision capabilities
- you lack GPU hardware for local inference and prefer a hosted API
- you need a lightweight model for edge or mobile deployment

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-inference, computer-vision, nlp, agent-framework
- domain: artificial-intelligence, machine-learning, computer-vision, large-language-models
- platform: python, cross-platform
- tags: vision-language-model, multimodal-reasoning, reinforcement-learning, vlm, image-understanding, video-understanding, image2text, open-weights, glm, natural-language-processing, ai-agents, gpu, linux

## Member repositories
- zai-org/GLM-V (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:41.777966+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 2026-08-30T02:35:25.765714+00:00, confidence not recorded.
  - readme: https://github.com/zai-org/GLM-V (fetched 2026-08-28T04:06:41.777966+00:00, sha 6ad5f59a287f)
- Data as of 2026-08-30T08:39:29.467469+00:00.