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

mradermacher/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-GGUF

mradermacher Qwen 35B 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-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-GGUF"
Response includes
  • classification m8
  • files 15
  • hub_downloads_all_time 26,168
  • author_summary 3324 models
  • readme_text full
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
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-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated' (base is huihui-ai model (M3))
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
26K
826 last 30d - cooling
Likes
9
Model age
6mo ago
created 2026-03-17
Downloads over time
Now26.7K→from3.8K↑609%
2.6K11.4K20.2K29K3.8K on Mar 1826.7K on Oct 11MarAprMayJunJulAugSepOct
Mar 18 → Oct 11 · 70 snapshots · spans 207 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.

Variants by this author 2 formats · 2K 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 Claude reasoning chain-of-thought Dense en base_model:huihui-ai/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated base_model:quantized:huihui-ai/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated license:apache-2.0

Related

Total size
221 GB
Files
15
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2026-10-07 01:53

Files by quantization

Q8_0 2 files 34.9 GB
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.Q8_0.gguf 34.4 GB 9d392ac8 download
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.mmproj-Q8_0.gguf 586 MB fc3b5ea6 download
Q6_K 1 file 26.6 GB
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.Q6_K.gguf 26.6 GB ea269fa3 download
Q5_K 2 files 45.4 GB
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.Q5_K_M.gguf 23.0 GB 0832a56e download
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.Q5_K_S.gguf 22.3 GB dd4d0241 download
Q4_K 2 files 38.2 GB
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.Q4_K_M.gguf 19.7 GB 64d10526 download
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.Q4_K_S.gguf 18.5 GB 0fccb0ac download
IQ4 1 file 17.6 GB
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.IQ4_XS.gguf 17.6 GB 7b3e2726 download
Q3_K 3 files 46.6 GB
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.Q3_K_L.gguf 16.9 GB 81c6eb74 download
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.Q3_K_M.gguf 15.6 GB 2132e4b3 download
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.Q3_K_S.gguf 14.1 GB 1ff18ce5 download
Q2_K 1 file 12.1 GB
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.Q2_K.gguf 12.1 GB 71b8eb2e download
F16 1 file 858 MB
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.mmproj-f16.gguf 858 MB 3c67b55f download
Auxiliary files 2 files 7.46 KB
README.md 4.82 KB b9daa4b9 download
.gitattributes 2.64 KB ea9e45a6 download

README current version from Hugging Face


base_model: huihui-ai/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated
language:


About

static quants of https://huggingface.co/huihui-ai/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-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-Qwen3.5-35B-A3B-Claude-4.6-Opus-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 0.7 multi-modal supplement
GGUF mmproj-f16 1.0 multi-modal supplement
GGUF Q2_K 13.0
GGUF Q3_K_S 15.3
GGUF Q3_K_M 16.9 lower quality
GGUF Q3_K_L 18.2
GGUF IQ4_XS 19.0
GGUF Q4_K_S 20.0 fast, recommended
GGUF Q4_K_M 21.3 fast, recommended
GGUF Q5_K_S 24.1
GGUF Q5_K_M 24.8
GGUF Q6_K 28.6 very good quality
GGUF Q8_0 37.0 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 6 versions

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

  1. 2026-10-07auto-patch README.md94fb1ec5 KB
    Loading...
  2. 2026-03-17auto-patch README.mddc071644.8 KB
    Loading...
  3. 2026-03-17auto-patch README.md78ee3464.9 KB
    Loading...
  4. 2026-03-17auto-patch README.mdc7924494.7 KB
    Loading...
  5. 2026-03-17auto-patch README.md9737b844.1 KB
    Loading...
  6. 2026-03-17uploaded from nico1e652ce0403 B
    Loading...

Discussions 1 thread

  1. 2026-03-244bit awqopen2 💬#1
    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.

Open in Abliteration