← back to catalog · registered 2026-09-04 08:03

micymike/Qwen2.5-Coder-3B-Abliterated-GGUF

Name: micymike/Qwen2.5-Coder-3B-Abliterated-GGUF
Author: micymike

Your rig guess connected

? Why do I need an app?

Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/micymike%2FQwen2.5-Coder-3B-Abliterated-GGUF"

Response includes

classification m8
files 5
hub_downloads_all_time 253
author_summary 2 models
readme_text full

10 credits · hourly refresh · ~4 KB payload Get an API key →

Abliteration classifier · v1.0.0

Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.

Confidence

MEDIUM

Inherited from base model

M1 Direct removal →

Why this label 3 signals

Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.

'abliterated' in name/tags
is_gguf=1
assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown

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 · lifetime

253

40 last 30d - stable

Likes

Model age

6w ago

created 2026-09-04

Downloads over time

Sep 4 → Oct 19 · 46 snapshots · spans 45 days

Variants by this author 2 formats · 319 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

micymike/Qwen2.5-Coder-3B-Abliterated GGUF 279
micymike/Qwen2.5-Coder-3B-Abliterated-GGUF (this) GGUF 40

Metadata

Quantizations

F16 Q4_K Q8_0

Files by quantization

F16 1 file 5.75 GB

qwen2.5-3b-abliterated-fp16.gguf

5.75 GB

7616e600

download

Q8_0 1 file 3.06 GB

qwen2.5-3b-abliterated-Q8_0.gguf

3.06 GB

47b71f9e

download

Q4_K 1 file 1.80 GB

qwen2.5-3b-abliterated-Q4_K_M.gguf

1.80 GB

1283f36b

download

Auxiliary files 2 files 2.65 KB

.gitattributes	1.69 KB	7b996501	download
README.md	987 B	3c220980	download

README current version from Hugging Face

tags:

qwen
qwen2.5
uncensored
abliterated
representation-engineering
gguf

Qwen2.5-Coder-3B-Abliterated-GGUF

These are the GGUF format quantized files for the abliterated (uncensored) version of the Qwen/Qwen2.5-Coder-3B-Instruct model.
The original model's refusal mechanisms were mathematically projected out using orthogonalization techniques (representation engineering).

Available Quantizations

FP16: Base format, highest quality, largest size.
Q8_0: Very high quality, almost indistinguishable from FP16, but smaller.
Q4_K_M: The recommended standard. Excellent balance between file size and generation quality.

Disclaimer

The creator of this model is NOT liable for any misuse, illegal activities, or harmful outputs generated by this model.
By using this model, you agree to take full responsibility for any consequences that arise from its application. This model is provided strictly for educational and research purposes.

README history 1 version

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

2026-09-04Upload README.md with huggingface_hubf363c4b987 B
Loading...

micymike/Qwen2.5-Coder-3B-Abliterated-GGUF

The browser can't see your hardware

The Abliteration app is integrated with your machine

And you can chat with any model, right now

Repackaging (quantization)

Variants by this author 2 formats · 319 downloads combined

Metadata

Related

Files by quantization

README current version from Hugging Face

Qwen2.5-Coder-3B-Abliterated-GGUF

Available Quantizations

Disclaimer

README history 1 version

Run models on your own machine, not in the cloud.