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

muzzy/GLM-5.2-FP8-DFlash-GGUF overview

This is an attempted conversion of https://huggingface.co/UCloud org/GLM 5.2 FP8 DFlash to gguf format. Both models function in ik llama, but I cannot get eith…

ggufbase_model:UCloud-org/GLM-5.2-FP8-DFlashbase_model:quantized:UCloud-org/GLM-5.2-FP8-DFlashendpoints_compatibleregion:usfeature-extraction

Runs locally from ~6.95 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
Author

Repository Files & Downloads

2 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
GLM-5.2-DFlash-glm4-tokenizer.ggufGGUFGGUF6.95 GBDownload
GLM-5.2-DFlash-llama3-tokenizer.ggufGGUFGGUF6.95 GBDownload

Model Details

Model IDmuzzy/GLM-5.2-FP8-DFlash-GGUF
Authormuzzy
Pipeline
License
Base modelUCloud-org/GLM-5.2-FP8-DFlash
Last modified2026-08-14T18:14:59.000Z

Model README

---

base_model: "UCloud-org/GLM-5.2-FP8-DFlash"

---

This is an attempted conversion of https://huggingface.co/UCloud-org/GLM-5.2-FP8-DFlash to gguf format. Both models function in ik_llama, but I cannot get either to get higher than 5% acceptance. I'm not sure which tokenizer to use, I think is the problem.

Run muzzy/GLM-5.2-FP8-DFlash-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