Zynerji/Ektome-Qwen3.5-9B-PristinelyUncensored-frac085-GGUF overview
Ektome Qwen3.5 9B PristinelyUncensored frac085 — GGUF | file | size | | | :| | q9b f085 Q4 K M.gguf | 5.2 GiB | | mmproj q9b f085 f16.gguf | 0.86 GiB | The mmp…
Runs locally from ~879.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
Model README
---
license: apache-2.0
base_model: Zynerji/Ektome-Qwen3.5-9B-PristinelyUncensored-frac085
tags: [ektome, uncensored, gguf, llama.cpp, vision]
---
Ektome-Qwen3.5-9B-PristinelyUncensored-frac085 — GGUF
| file | size |
|---|---:|
| q9b_f085-Q4_K_M.gguf | 5.2 GiB |
| mmproj-q9b_f085-f16.gguf | 0.86 GiB |
The mmproj file is required for vision. convert_hf_to_gguf.py exported 427 of this
model's 760 tensors — the language decoder only — and reported success. The 333 vision tensors
are in the mmproj file.
llama-cli -m q9b_f085-Q4_K_M.gguf --mmproj mmproj-q9b_f085-f16.gguf ...Receipts and the gate-threshold caveat: see
Run Zynerji/Ektome-Qwen3.5-9B-PristinelyUncensored-frac085-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models