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

Phil2Sat/Qwen-3.8-27B-Uncensored-I-Compact.gguf_ALPHA_TESTING overview

Frankenquant of Ektome Qwen3.8 27B PristinelyUncensored. Goal is to fit into 16GB Vram, did my best, dunnow what im doin, pre alpha, but works so far. MTP is i…

ggufbase_model:Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensoredbase_model:quantized:Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensoredendpoints_compatibleregion:usimatrixconversational

Runs locally from ~13.91 GB disk (16 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
1
Pipeline
Author

Repository Files & Downloads

1 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Qwen-3.8-27B-Uncensored-I-Compact-MXFP4.ggufGGUFGGUF13.91 GBDownload

Model Details

Model IDPhil2Sat/Qwen-3.8-27B-Uncensored-I-Compact.gguf_ALPHA_TESTING
AuthorPhil2Sat
Pipeline
License
Base modelZynerji/Ektome-Qwen3.8-27B-PristinelyUncensored
Last modified2026-08-15T08:43:43.000Z

Model README

---

base_model:

  • Zynerji/Ektome-Qwen3.8-27B-PristinelyUncensored

---

Frankenquant of Ektome-Qwen3.8-27B-PristinelyUncensored.

Goal is to fit into 16GB Vram, did my best, dunnow what im doin, pre alpha, but works so far.

MTP is included.

My first tests shows no refusals at all in RP.

Run Phil2Sat/Qwen-3.8-27B-Uncensored-I-Compact.gguf_ALPHA_TESTING 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