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

mradermacher/Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2-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%2FQwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2-GGUF"
Response includes
  • classification m8
  • files 13
  • hub_downloads_all_time 10,785
  • 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 direct removal 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='DavidAU/Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2' (base has 'abliterated' marker, assume M1 default)
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
11K
895 last 30d - cooling
Likes
2
Model age
7mo ago
created 2026-02-15

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

Downloads over time
Now11K→from1.5K↑652%
9844.6K8.3K11.9K1.5K on Feb 1811K on Oct 11FebAprJunAugOct
Feb 18 → Oct 11 · 73 snapshots · spans 235 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 · 4K 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 finetune unsloth abliterated uncensored specialized post tuning claude-4.5-opus reasoning thinking distill-fine-tune moe

Related

Total size
194 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-02-16 18:08

Files by quantization

Q8_0 1 file 30.3 GB
Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2.Q8_0.gguf 30.3 GB 20a34ec6 download
Q6_K 1 file 23.4 GB
Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2.Q6_K.gguf 23.4 GB 99479cc6 download
Q5_K 2 files 39.9 GB
Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2.Q5_K_M.gguf 20.2 GB bb42cd1a download
Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2.Q5_K_S.gguf 19.6 GB 0d3e2a78 download
Q4_K 2 files 33.5 GB
Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2.Q4_K_M.gguf 17.3 GB 52ecbe7a download
Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2.Q4_K_S.gguf 16.3 GB 55373615 download
IQ4 1 file 15.4 GB
Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2.IQ4_XS.gguf 15.4 GB ea71c5af download
Q3_K 3 files 40.9 GB
Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2.Q3_K_L.gguf 14.8 GB 9e4c10d1 download
Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2.Q3_K_M.gguf 13.7 GB a4533c05 download
Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2.Q3_K_S.gguf 12.4 GB d51124a0 download
Q2_K 1 file 10.5 GB
Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2.Q2_K.gguf 10.5 GB 070b2956 download
Auxiliary files 2 files 7.86 KB
README.md 5.05 KB ce6d99d0 download
.gitattributes 2.81 KB 03e2111f download

README current version from Hugging Face


base_model: DavidAU/Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2
datasets:

  • TeichAI/claude-4.5-opus-high-reasoning-250x
    language:
  • en
    library_name: transformers
    license: apache-2.0
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • finetune
  • unsloth
  • abliterated
  • uncensored
  • specialized post tuning
  • claude-4.5-opus
  • reasoning
  • thinking
  • distill-fine-tune
  • moe
  • 128 experts
  • 256k context
  • mixture of experts

About

static quants of https://huggingface.co/DavidAU/Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2

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

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2-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 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 5 versions

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

  1. 2026-02-16auto-patch README.md11425e25.1 KB
    Loading...
  2. 2026-02-15auto-patch README.md57613655.1 KB
    Loading...
  3. 2026-02-15auto-patch README.md0ac5cda4.9 KB
    Loading...
  4. 2026-02-15auto-patch README.md19ffb392.6 KB
    Loading...
  5. 2026-02-15uploaded from marco1cb52a6426 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.

Open in Abliteration