#2929th of 70 in Open models
glm-v
Open-weight GLM-4.6V, 4.5V and 4.1V vision-language models with examples
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 2.4k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Language
- Python
2,246 on 21 Apr 20262,404 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Repository for Zhipu/Z.ai's GLM-4.6V, GLM-4.5V and GLM-4.1V vision-language models, linking weights on Hugging Face and ModelScope (including FP8 and GGUF variants). It adds example code for GUI agents, a desktop chat helper, a VLM reward system, and LLaMA-Factory fine-tuning notes. The maintainers state the repo is no longer maintained as of 2026/09/02.
Who it is for: Engineers self-hosting open vision-language models
Strengths
- Covers 106B GLM-4.6V, 9B GLM-4.6V-Flash and 9B GLM-4.1V-9B-Thinking checkpoints
- GLM-4.6V offers native multimodal function calling and 128K context
- Serving supported in SGLang, vLLM and Transformers; GGUF and FP8 weights available
- Includes bounding-box grounding, GUI agent examples and Midscene.js demos
Weaknesses
- Repository declared unmaintained as of 2026/09/02; newer work moved to the GLM-5 repo
- No tagged releases; weights live on external hosts
- Known issues: repetitive thinking, weak text-only QA, counting errors
What it needs
- Needs SGLang, vLLM, Transformers, LLaMA-Factory
- Models: GLM-4.6V, GLM-4.6V-FP8, GLM-4.6V-Flash, GLM-4.5V, GLM-4.5V-FP8
Quick answers
Is glm-v open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Also in Open models
See all 70| Rank | Project | Score |
|---|---|---|
| 1 | ruviewWiFi CSI sensing on ESP32 for presence, breathing, heart rate and pose | 94 out of 100 |
| 2 | layaSingle-pass multilingual classifier for typed choice, score and yes/no decisions | 88 out of 100 |
| 3 | rf-detrReal-time transformer models for object detection, segmentation and keypoints | 79 out of 100 |
| #4 | timesfmPretrained time-series foundation model for zero-shot forecasting from Google Research | 78 out of 100 |
| #5 | yolov5PyTorch YOLOv5 object detection, segmentation and classification models with training code | 76 out of 100 |