GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

jamiefutch/GLM-4.6V-MXFP4_MOE-GGUF overview

This is a imatrix MXFP4 MOE quantization of the model GLM 4.6V https://huggingface.co/zai org/GLM 4.6V , based on the imatrix from unsloth. Get the latest llam…

ggufimage-text-to-textbase_model:zai-org/GLM-4.6Vbase_model:quantized:zai-org/GLM-4.6Vendpoints_compatibleregion:usimatrixconversational

Runs locally from ~948.4 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
1
Pipeline
image-text-to-text

Repository Files & Downloads

8 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
GLM-4.6V-MXFP4_MOE-00001-of-00004.ggufGGUFGGUF14.56 GBDownload
GLM-4.6V-MXFP4_MOE-00002-of-00004.ggufGGUFGGUF14.67 GBDownload
GLM-4.6V-MXFP4_MOE-00003-of-00004.ggufGGUFGGUF14.67 GBDownload
GLM-4.6V-MXFP4_MOE-00004-of-00004.ggufGGUFGGUF12.60 GBDownload
mmproj-BF16.ggufGGUFBF161.65 GBDownload
mmproj-F16.ggufGGUFF161.60 GBDownload
mmproj-F32.ggufGGUFF323.20 GBDownload
mmproj-Q8_0.ggufGGUFQ8_0948.4 MBDownload

Model Details

Model IDjamiefutch/GLM-4.6V-MXFP4_MOE-GGUF
Authorjamiefutch
Pipelineimage-text-to-text
License
Base modelzai-org/GLM-4.6V
Last modified2026-07-06T09:42:50.000Z

Model README

---

pipeline_tag: image-text-to-text

base_model:

  • zai-org/GLM-4.6V

---

This is a imatrix MXFP4_MOE quantization of the model GLM-4.6V, based on the imatrix from unsloth.

Get the latest llama.cpp in order to run it.

For the mmproj, try to use the largest version you can fit in memory in order to get the best results.

F32 > BF16 > F16 > Q8_0.

Run jamiefutch/GLM-4.6V-MXFP4_MOE-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models