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

mradermacher/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-GGUF

mradermacher Qwen 30B GGUF MoE second-order 262K 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%2FHuihui-Qwen3-VL-30B-A3B-Instruct-abliterated-GGUF"
Response includes
  • classification m8
  • files 15
  • hub_downloads_all_time 39,155
  • author_summary 3324 models
  • readme_text full
Try next
GET/models?author=mradermacher
All 3324 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 layer-wise ablation inherited from the base model.
Confidence
HIGH
Inherited from base model
M3 Layer-wise ablation →
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='huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated' (base is huihui-ai model (M3))
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
39K
12K last 30d - stable
Likes
5
Model age
11mo ago
created 2025-11-03
Downloads over time
Now40.4K→from742↑5,349%
014.8K29.6K44.4K742 on Nov 5, 202540.4K on Oct 11Nov '25JanMarMayJulSep
Nov 5, 2025 → Oct 11 · 90 snapshots · spans 340 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.

huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated↓ 3,189 this lineage
mradermacher/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-GGUF↓ 12,089

Variants by this author 2 formats · 21K downloads combined

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

Metadata

License
apache-2.0
Languages
en
Quantizations
IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf abliterated uncensored en base_model:huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated base_model:quantized:huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated license:apache-2.0 endpoints_compatible region:us conversational

Related

Other by mradermacher
Ornith-1.5-9B-uncensored-GGUF 1.5M Qwen3-VL-8B-Instruct-abliterated-GGUF 667K Qwen3.8-Flash-Next-Uncensored-i1-GGUF 153K gemma-4-26B-A4B-it-ultra-uncensored-heretic-i1-GGUF 138K Qwen3.8-9B-heretic-uncensored-GGUF 106K
Same base model
noctrex/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-GGUF 15K mradermacher/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-i1-GGUF 8K Tipur/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-GGUF 591 McG-221/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-Q8_0-GGUF 547 MLXBits/huihui-qwen3-vl-30b-abliterated-4bit 99
Total size
194 GB
Files
15
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2025-11-03 12:19
Source huggingface.co/mradermacher/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-GGUF ↗ Base model huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated →

Files by quantization

Q8_0 2 files 30.9 GB
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.Q8_0.gguf 30.3 GB a610243f download
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.mmproj-Q8_0.gguf 679 MB 4dcdbf32 download
Q6_K 1 file 23.4 GB
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.Q6_K.gguf 23.4 GB 80a66cef download
Q5_K 2 files 39.9 GB
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.Q5_K_M.gguf 20.2 GB 36243e0a download
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.Q5_K_S.gguf 19.6 GB 856bde21 download
Q4_K 2 files 33.5 GB
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.Q4_K_M.gguf 17.3 GB 157808ca download
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.Q4_K_S.gguf 16.3 GB c11b8c1b download
IQ4 1 file 15.4 GB
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.IQ4_XS.gguf 15.4 GB 85ec3c1d download
Q3_K 3 files 40.9 GB
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.Q3_K_L.gguf 14.8 GB 6b13897a download
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.Q3_K_M.gguf 13.7 GB 4665eb44 download
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.Q3_K_S.gguf 12.4 GB 9b97b2b0 download
Q2_K 1 file 10.5 GB
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.Q2_K.gguf 10.5 GB a973ea08 download
F16 1 file 1.01 GB
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.mmproj-f16.gguf 1.01 GB 4bfd6558 download
Auxiliary files 2 files 7.15 KB
README.md 4.48 KB 6495fa40 download
.gitattributes 2.67 KB 5ccc8639 download

README current version from Hugging Face

base_model: huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated
language:

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

About

static quants of https://huggingface.co/huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated

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

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-i1-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 mmproj-Q8_0 0.8 multi-modal supplement
GGUF mmproj-f16 1.2 multi-modal supplement
GGUF Q2_K 11.4
GGUF Q3_K_S 13.4
GGUF Q3_K_M 14.8 lower quality
GGUF Q3_K_L 16.0
GGUF IQ4_XS 16.7
GGUF Q4_K_S 17.6 fast, recommended
GGUF Q4_K_M 18.7 fast, recommended
GGUF Q5_K_S 21.2
GGUF Q5_K_M 21.8
GGUF Q6_K 25.2 very good quality
GGUF Q8_0 32.6 fast, best quality

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.

README history 4 versions

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

  1. 2025-11-03auto-patch README.md36c375b4.5 KB
    Loading...
  2. 2025-11-03auto-patch README.mde1224044.6 KB
    Loading...
  3. 2025-11-03auto-patch README.md507f4814.4 KB
    Loading...
  4. 2025-11-03uploaded from nico1cfb4637397 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