← back to catalog · registered 2026-09-14 23:56

brandonbondig/orcarouter_Qwen3.8-27B-Uncensored-Q5_K_M-GGUF

Name: brandonbondig/orcarouter_Qwen3.8-27B-Uncensored-Q5_K_M-GGUF
Author: brandonbondig

Abliteration classifier · v1.0.0

M-U

Primary method

Uncensored (method unknown)

No other method signals detected in this model.

Confidence

LOW

Why this label 3 signals

Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.

'uncensored' in name/tags but no 'abliterated' marker
method not identifiable from author declaration alone
may be DPO fine-tune, prompt engineering, or unknown technique

Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

Downloads · 30-day

Likes

Model age

today

created 2026-09-14

Downloads over time

Sep 14 → Sep 15 · 2 snapshots · spans 1 day

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

bartowski/orcarouter_Qwen3.8-27B-Uncensored-GGUF↓ 104,886 this lineage

brandonbondig/orcarouter_Qwen3.8-27B-Uncensored-Q5_K_M-GGUF↓ 45

Metadata

License

apache-2.0

Quantizations

Q5_K

Files by quantization

Q5_K 1 file 19.3 GB

orcarouter_Qwen3.8-27B-Uncensored-Q5_K_M.gguf

19.3 GB

4ad98832

download

Auxiliary files 3 files 2.47 KB

.gitattributes	1.56 KB	99fd7feb	download
README.md	817 B	8cd80cb2	download
SHA256SUMS	112 B	42dd6131	download

README current version from Hugging Face

license: apache-2.0
base_model: bartowski/orcarouter_Qwen3.8-27B-Uncensored-GGUF
base_model_relation: quantized
tags:

gguf
llama.cpp
runpod

orcarouter_Qwen3.8-27B-Uncensored-Q5_K_M-GGUF

Single-file mirror of orcarouter_Qwen3.8-27B-Uncensored-Q5_K_M.gguf from bartowski/orcarouter_Qwen3.8-27B-Uncensored-GGUF,
published so RunPod's cached-models feature stages one 20.8 GB file instead of the whole quant ladder.

The file is byte-identical to upstream (SHA256SUMS carries the upstream checksum). The quantisation
is bartowski's imatrix build of orcarouter/Qwen3.8-27B-Uncensored;
see those repos for the model card, licence, prompt format, and calibration data.

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

2026-09-14Add README.mdce9e2c1817 B
Loading...