Get the app
← back to catalog · registered 2026-08-22 13:56

mradermacher/qwen3-0.6b-abliterated-i1-GGUF

mradermacher Qwen 600M GGUF second-order 41K ctx
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/mradermacher%2Fqwen3-0.6b-abliterated-i1-GGUF"
Response includes
  • classification m8
  • files 27
  • hub_downloads_all_time 3,012
  • author_summary 3328 models
  • readme_text full
Try next
GET/models?author=mradermacher
All 3328 models by mradermacher
 GET/models?family=qwen&method=m8
Sibling qwen models · same method
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
M1 Direct removal →
Why this label 3 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • author=mradermacher (M8 quantization producer, never originator)
  • is_gguf=1
  • base_model='ops-malware/qwen3-0.6b-abliterated' (base has 'abliterated' marker, assume M1 default)
How we label → About M8 →
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.

What is a refusal direction? →
Downloads · lifetime
3K
2K last 30d - active
Likes
0
Model age
2mo ago
created 2026-07-28
Downloads over time
Now4.4K→from0↑0%
01.6K3.2K4.8K0 on Jul 294.4K on Oct 12JulAugSepOct
Jul 29 → Oct 12 · 52 snapshots · spans 75 days

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.

ops-malware/qwen3-0.6b-abliterated↓ 256 this lineage
mradermacher/qwen3-0.6b-abliterated-i1-GGUF↓ 1,901

Metadata

License
apache-2.0
Languages
en
Quantizations
IQ1 IQ2 IQ3 IQ4 Q2_K Q3_K Q4 Q4_K Q5_K Q6_K
Tags
transformers gguf abliterated uncensored refusal-removal interpretability senbonzakura en base_model:ElementMerc/qwen3-0.6b-abliterated base_model:quantized:ElementMerc/qwen3-0.6b-abliterated license:apache-2.0 endpoints_compatible

Related

Other by mradermacher
Ornith-1.5-9B-uncensored-GGUF 1.5M Qwen3-VL-8B-Instruct-abliterated-GGUF 668K Qwen3.8-Flash-Next-Uncensored-i1-GGUF 148K gemma-4-26B-A4B-it-ultra-uncensored-heretic-i1-GGUF 133K Qwen3.8-9B-heretic-uncensored-GGUF 107K
Same base model
ElementMerc/qwen3-0.6b-abliterated-GGUF 182 ops-malware/qwen3-0.6b-abliterated-GGUF 124
Total size
7.43 GB
Files
27
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2026-10-06 04:29
Source huggingface.co/mradermacher/qwen3-0.6b-abliterated-i1-GGUF ↗ Base model ops-malware/qwen3-0.6b-abliterated →

Files by quantization

Q6_K 1 file 472 MB
qwen3-0.6b-abliterated.i1-Q6_K.gguf 472 MB 2f7e4173 download
Q5_K 2 files 840 MB
qwen3-0.6b-abliterated.i1-Q5_K_M.gguf 424 MB bb9c22fc download
qwen3-0.6b-abliterated.i1-Q5_K_S.gguf 416 MB a6e272a5 download
Q4 2 files 755 MB
qwen3-0.6b-abliterated.i1-Q4_1.gguf 390 MB ca313fea download
qwen3-0.6b-abliterated.i1-Q4_0.gguf 364 MB e824fe7f download
Q4_K 2 files 744 MB
qwen3-0.6b-abliterated.i1-Q4_K_M.gguf 378 MB f7a51518 download
qwen3-0.6b-abliterated.i1-Q4_K_S.gguf 366 MB e2842878 download
IQ4 2 files 715 MB
qwen3-0.6b-abliterated.i1-IQ4_NL.gguf 364 MB 66f40905 download
qwen3-0.6b-abliterated.i1-IQ4_XS.gguf 351 MB 2427c54e download
Q3_K 3 files 991 MB
qwen3-0.6b-abliterated.i1-Q3_K_L.gguf 351 MB 562f191e download
qwen3-0.6b-abliterated.i1-Q3_K_M.gguf 331 MB 3c5359af download
qwen3-0.6b-abliterated.i1-Q3_K_S.gguf 308 MB 171572e0 download
IQ3 4 files 1.16 GB
qwen3-0.6b-abliterated.i1-IQ3_M.gguf 320 MB d3ef167f download
qwen3-0.6b-abliterated.i1-IQ3_S.gguf 308 MB 225ed63a download
qwen3-0.6b-abliterated.i1-IQ3_XS.gguf 298 MB 3745f63a download
qwen3-0.6b-abliterated.i1-IQ3_XXS.gguf 266 MB 2daea4a5 download
Q2_K 2 files 550 MB
qwen3-0.6b-abliterated.i1-Q2_K.gguf 283 MB 06712457 download
qwen3-0.6b-abliterated.i1-Q2_K_S.gguf 268 MB 24f3e9e9 download
IQ2 4 files 945 MB
qwen3-0.6b-abliterated.i1-IQ2_M.gguf 253 MB 1ea46d1c download
qwen3-0.6b-abliterated.i1-IQ2_S.gguf 242 MB 798de3b9 download
qwen3-0.6b-abliterated.i1-IQ2_XS.gguf 231 MB 42fca5fc download
qwen3-0.6b-abliterated.i1-IQ2_XXS.gguf 219 MB 6ed8cba9 download
IQ1 2 files 404 MB
qwen3-0.6b-abliterated.i1-IQ1_M.gguf 206 MB 59662ceb download
qwen3-0.6b-abliterated.i1-IQ1_S.gguf 198 MB d8ef589a download
Auxiliary files 3 files 1.13 MB
qwen3-0.6b-abliterated.imatrix.gguf 1.12 MB 7dea0e33 download
README.md 6.21 KB a20c1b80 download
.gitattributes 3.28 KB 0422683f download

README current version from Hugging Face

base_model: ops-malware/qwen3-0.6b-abliterated
language:

  • en
    library_name: transformers
    license: apache-2.0
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • abliterated
  • uncensored
  • refusal-removal
  • interpretability
  • senbonzakura

About

weighted/imatrix quants of https://huggingface.co/ops-malware/qwen3-0.6b-abliterated

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/qwen3-0.6b-abliterated-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs for
more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF imatrix 0.1 imatrix file (for creating your own quants)
GGUF i1-IQ1_S 0.3 for the desperate
GGUF i1-IQ1_M 0.3 mostly desperate
GGUF i1-IQ2_XXS 0.3
GGUF i1-IQ2_XS 0.3
GGUF i1-IQ2_S 0.4
GGUF i1-IQ2_M 0.4
GGUF i1-IQ3_XXS 0.4 lower quality
GGUF i1-Q2_K_S 0.4 very low quality
GGUF i1-Q2_K 0.4 IQ3_XXS probably better
GGUF i1-IQ3_XS 0.4
GGUF i1-IQ3_S 0.4 beats Q3_K*
GGUF i1-Q3_K_S 0.4 IQ3_XS probably better
GGUF i1-IQ3_M 0.4
GGUF i1-Q3_K_M 0.4 IQ3_S probably better
GGUF i1-IQ4_XS 0.5
GGUF i1-Q3_K_L 0.5 IQ3_M probably better
GGUF i1-IQ4_NL 0.5 prefer IQ4_XS
GGUF i1-Q4_0 0.5 fast, low quality
GGUF i1-Q4_K_S 0.5 optimal size/speed/quality
GGUF i1-Q4_K_M 0.5 fast, recommended
GGUF i1-Q4_1 0.5
GGUF i1-Q5_K_S 0.5
GGUF i1-Q5_K_M 0.5
GGUF i1-Q6_K 0.6 practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

image.png

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

README history 3 versions

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

  1. 2026-10-06auto-patch README.mdb18a7586.2 KB
    Loading...
  2. 2026-07-28auto-patch README.mdb7786476.2 KB
    Loading...
  3. 2026-07-28uploaded from backebd44a1480 B
    Loading...
Catalog is the map. Apps are the tools.

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

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration