GLM-4.6V-Flash-GGUF

<span style="color: #7FFF7F;">GLM-4.6V-Flash GGUF Models</span>

<span style="color: #7F7FFF;">Model Generation Details</span>

This model was generated using llama.cpp at commit e1f15b454.

---

<span style="color: #7FFF7F;">Quantization Beyond the IMatrix</span>

I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.

In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the --tensor-type option in llama.cpp to manually "bump" important layers to higher precision. You can see the implementation here:
👉 Layer bumping with llama.cpp

While this does increase model file size, it significantly improves precision for a given quantization level.

I'd love your feedback—have you tried this? How does it perform for you?

---

<a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;"> Click here to get info on choosing the right GGUF model format </a>

---

<!--Begin Original Model Card-->

GLM-4.6V

<div align="center"> <img src=https://raw.githubusercontent.com/zai-org/GLM-V/refs/heads/main/resources/logo.svg width="40%"/> </div>

This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

• GLM-4.6V Blog: https://z.ai/blog/glm-4.6v
• Paper: https://huggingface.co/papers/2507.01006
• GitHub Repository: https://github.com/zai-org/GLM-V
• Online Demo: https://chat.z.ai/
• API Access: Z.ai Open Platform
• Desktop Assistant App: https://huggingface.co/spaces/zai-org/GLM-4.5V-Demo-App

Introduction

GLM-4.6V series model includes two versions: GLM-4.6V (106B), a foundation model designed for cloud and high-performance cluster scenarios, and GLM-4.6V-Flash (9B), a lightweight model optimized for local deployment and low-latency applications. GLM-4.6V scales its context window to 128k tokens in training, and achieves SoTA performance in visual understanding among models of similar parameter scales. Crucially, we integrate native Function Calling capabilities for the first time. This effectively bridges the gap between "visual perception" and "executable action" providing a unified technical foundation for multimodal agents in real-world business scenarios.

Beyond achieves SoTA performance across major multimodal benchmarks at comparable model scales. GLM-4.6V introduces several key features:

• Native Multimodal Function Calling Enables native vision-driven tool use. Images, screenshots, and document pages can be passed directly as tool inputs without text conversion, while visual outputs (charts, search images, rendered pages) are interpreted and integrated into the reasoning chain. This closes the loop from perception to understanding to execution.

• Interleaved Image-Text Content Generation Supports high-quality mixed media creation from complex multimodal inputs. GLM-4.6V takes a multimodal context—spanning documents, user inputs, and tool-retrieved images—and synthesizes coherent, interleaved image-text content tailored to the task. During generation it can actively call search and retrieval tools to gather and curate additional text and visuals, producing rich, visually grounded content.

• Multimodal Document Understanding GLM-4.6V can process up to 128K tokens of multi-document or long-document input, directly interpreting richly formatted pages as images. It understands text, layout, charts, tables, and figures jointly, enabling accurate comprehension of complex, image-heavy documents without requiring prior conversion to plain text.

• Frontend Replication & Visual Editing Reconstructs pixel-accurate HTML/CSS from UI screenshots and supports natural-language-driven edits. It detects layout, components, and styles visually, generates clean code, and applies iterative visual modifications through simple user instructions.

This Hugging Face repository hosts the GLM-4.6V-Flash model, part of the GLM-V series.

Usage

Environment Installation

For SGLang:

pip install sglang>=0.5.6.post1
pip install nvidia-cudnn-cu12==9.16.0.29
sudo apt update
sudo apt install ffmpeg

For vLLM:

pip install vllm>=0.12.0
pip install transformers>=5.0.0rc0

Quick Start with Transformers

from transformers import AutoProcessor, Glm4vForConditionalGeneration
import torch

MODEL_PATH = "zai-org/GLM-4.6V-Flash"
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "url": "https://upload.wikimedia.org/wikipedia/commons/f/fa/Grayscale_8bits_palette_sample_image.png"
            },
            {
                "type": "text",
                "text": "describe this image"
            }
        ],
    }
]
processor = AutoProcessor.from_pretrained(MODEL_PATH)
model = Glm4vForConditionalGeneration.from_pretrained(
    pretrained_model_name_or_path=MODEL_PATH,
    torch_dtype="auto",
    device_map="auto",
)
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
).to(model.device)
inputs.pop("token_type_ids", None)
generated_ids = model.generate(**inputs, max_new_tokens=8192)
output_text = processor.decode(generated_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False)
print(output_text)

Evaluation Settings

We primarily use vLLM as the backend for model inference. For faster and more reliable performance on video tasks, we employ SGLang. To reproduce our leaderboard results, we recommend the following decoding parameters:

• top_p: 0.6
• top_k: 2
• temperature: 0.8
• repetition_penalty: 1.1
• max_generate_tokens: 16K

For more usage details, please refer to Our Github.

Fixed and Remaining Issues

Since the open-sourcing of GLM-4.1V, we have received extensive feedback from the community and are well aware that the model still has many shortcomings. In subsequent iterations, we attempted to address several common issues — such as repetitive thinking outputs and formatting errors — which have been mitigated to some extent in this new version.

However, the model still has several limitations and issues that we will fix as soon as possible:

1. Pure text QA capabilities still have significant room for improvement. In this development cycle, our primary focus was on visual multimodal scenarios, and we will enhance pure text abilities in upcoming updates.
2. The model may still overthink or even repeat itself in certain cases, especially when dealing with complex prompts.
3. In some situations, the model may restate the answer again at the end.
4. There remain certain perception limitations, such as counting accuracy and identifying specific individuals, which still require improvement.

Thank you for your patience and understanding. We also welcome feedback and suggestions in the issue section — we will respond and improve as much as we can!

Citation

If you use this model, please cite the following paper:

@misc{vteam2025glm45vglm41vthinkingversatilemultimodal,
      title={GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning}, 
      author={V Team and Wenyi Hong and Wenmeng Yu and Xiaotao Gu and Guo Wang and Guobing Gan and Haomiao Tang and Jiale Cheng and Ji Qi and Junhui Ji and Lihang Pan and Shuaiqi Duan and Weihan Wang and Yan Wang and Yean Cheng and Zehai He and Zhe Su and Zhen Yang and Ziyang Pan and Aohan Zeng and Baoxu Wang and Bin Chen and Boyan Shi and Changyu Pang and Chenhui Zhang and Da Yin and Fan Yang and Guoqing Chen and Jiazheng Xu and Jiale Zhu and Jiali Chen and Jing Chen and Jinhao Chen and Jinghao Lin and Jinjiang Wang and Junjie Chen and Leqi Lei and Letian Gong and Leyi Pan and Mingdao Liu and Mingde Xu and Mingzhi Zhang and Qinkai Zheng and Sheng Yang and Shi Zhong and Shiyu Huang and Shuyuan Zhao and Siyan Xue and Shangqin Tu and Shengbiao Meng and Tianshu Zhang and Tianwei Luo and Tianxiang Hao and Tianyu Tong and Wenkai Li and Wei Jia and Xiao Liu and Xiaohan Zhang and Xin Lyu and Xinyue Fan and Xuancheng Huang and Yanling Wang and Yadong Xue and Yanfeng Wang and Yanzi Wang and Yifan An and Yifan Du and Yiming Shi and Yiheng Huang and Yilin Niu and Yuan Wang and Yuanchang Yue and Yuchen Li and Yutao Zhang and Yuting Wang and Yu Wang and Yuxuan Zhang and Zhao Xue and Zhenyu Hou and Zhengxiao Du and Zihan Wang and Peng Zhang and Debing Liu and Bin Xu and Juanzi Li and Minlie Huang and Yuxiao Dong and Jie Tang},
      year={2025},
      eprint={2507.01006},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2507.01006}, 
}

<!--End Original Model Card-->

---

<span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>

Help me test my AI-Powered Quantum Network Monitor Assistant with quantum-ready security checks:

👉 Quantum Network Monitor

The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : Source Code Quantum Network Monitor. You will also find the code I use to quantize the models if you want to do it yourself GGUFModelBuilder

💬 How to test:
Choose an AI assistant type:

• TurboLLM (GPT-4.1-mini)
• HugLLM (Hugginface Open-source models)
• TestLLM (Experimental CPU-only)

What I’m Testing

I’m pushing the limits of small open-source models for AI network monitoring, specifically:

• Function calling against live network services
• How small can a model go while still handling:
  • Automated Nmap security scans
  • Quantum-readiness checks
  • Network Monitoring tasks

🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):

• ✅ Zero-configuration setup
• ⏳ 30s load time (slow inference but no API costs) . No token limited as the cost is low.
• 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate!

Other Assistants

🟢 TurboLLM – Uses gpt-4.1-mini :

• **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited.
• Create custom cmd processors to run .net code on Quantum Network Monitor Agents
• Real-time network diagnostics and monitoring
• Security Audits
• Penetration testing (Nmap/Metasploit)

🔵 HugLLM – Latest Open-source models:

• 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.

💡 Example commands you could test:

1. "Give me info on my websites SSL certificate"
2. "Check if my server is using quantum safe encyption for communication"
3. "Run a comprehensive security audit on my server"
4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code on. This is a very flexible and powerful feature. Use with caution!

Final Word

I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is open source. Feel free to use whatever you find helpful.

If you appreciate the work, please consider buying me a coffee ☕. Your support helps cover service costs and allows me to raise token limits for everyone.

I'm also open to job opportunities or sponsorship.

Thank you! 😊