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

AliceThirty/GLM-5.3-Flash-UNCENSORED-GGUF overview

Use with https://github.com/unslothai/llama.cpp/tree/glm5next/upstream

ggufbase_model:dealignai/GLM-5.3-Flash-UNCENSORED-FP8base_model:quantized:dealignai/GLM-5.3-Flash-UNCENSORED-FP8endpoints_compatibleregion:usimatrixconversational

Runs locally from ~1.08 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
4,572
Likes
7
Pipeline

Repository Files & Downloads

21 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
GLM-5.3-Flash-UNCENSORED-FP8-mmproj-bf16.ggufGGUFBF161.08 GBDownload
UD-IQ3_XXS/GLM-5.3-Flash-UNCENSORED-FP8-UD-IQ3_XXS-00001-of-00003.ggufGGUFIQ3_XXS45.12 GBDownload
UD-IQ3_XXS/GLM-5.3-Flash-UNCENSORED-FP8-UD-IQ3_XXS-00002-of-00003.ggufGGUFIQ3_XXS45.06 GBDownload
UD-IQ3_XXS/GLM-5.3-Flash-UNCENSORED-FP8-UD-IQ3_XXS-00003-of-00003.ggufGGUFIQ3_XXS22.12 GBDownload
UD-Q2_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q2_K_XL-00001-of-00003.ggufGGUFQ2_K_XL45.14 GBDownload
UD-Q2_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q2_K_XL-00002-of-00003.ggufGGUFQ2_K_XL45.63 GBDownload
UD-Q2_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q2_K_XL-00003-of-00003.ggufGGUFQ2_K_XL10.45 GBDownload
UD-Q3_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q3_K_XL-00001-of-00004.ggufGGUFQ3_K_XL45.25 GBDownload
UD-Q3_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q3_K_XL-00002-of-00004.ggufGGUFQ3_K_XL44.93 GBDownload
UD-Q3_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q3_K_XL-00003-of-00004.ggufGGUFQ3_K_XL44.99 GBDownload
UD-Q3_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q3_K_XL-00004-of-00004.ggufGGUFQ3_K_XL2.00 GBDownload
UD-Q4_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q4_K_XL-00001-of-00005.ggufGGUFQ4_K_XL44.47 GBDownload
UD-Q4_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q4_K_XL-00002-of-00005.ggufGGUFQ4_K_XL45.42 GBDownload
UD-Q4_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q4_K_XL-00003-of-00005.ggufGGUFQ4_K_XL45.17 GBDownload
UD-Q4_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q4_K_XL-00004-of-00005.ggufGGUFQ4_K_XL45.59 GBDownload
UD-Q4_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q4_K_XL-00005-of-00005.ggufGGUFQ4_K_XL5.55 GBDownload
UD-Q5_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q5_K_XL-00001-of-00005.ggufGGUFQ5_K_XL45.51 GBDownload
UD-Q5_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q5_K_XL-00002-of-00005.ggufGGUFQ5_K_XL45.27 GBDownload
UD-Q5_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q5_K_XL-00003-of-00005.ggufGGUFQ5_K_XL44.27 GBDownload
UD-Q5_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q5_K_XL-00004-of-00005.ggufGGUFQ5_K_XL44.41 GBDownload
UD-Q5_K_XL/GLM-5.3-Flash-UNCENSORED-FP8-UD-Q5_K_XL-00005-of-00005.ggufGGUFQ5_K_XL44.55 GBDownload

Model Details

Model IDAliceThirty/GLM-5.3-Flash-UNCENSORED-GGUF
AuthorAliceThirty
Pipeline
License
Base modeldealignai/GLM-5.3-Flash-UNCENSORED-FP8
Last modified2026-09-02T13:49:03.000Z

Model README

---

base_model:

  • dealignai/GLM-5.3-Flash-UNCENSORED-FP8

---

Use with https://github.com/unslothai/llama.cpp/tree/glm5next/upstream

Run AliceThirty/GLM-5.3-Flash-UNCENSORED-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