← back to catalog · registered 2026-08-26 15:02

mradermacher/SuperQwen3.8-abliterated-Venice-GGUF

mradermacher Qwen GGUF multimodal 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%2FSuperQwen3.8-abliterated-Venice-GGUF"
Response includes
  • classification m8
  • files 15
  • hub_downloads_all_time 1,965
  • 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='Jiunsong/SuperQwen3.8-abliterated-100-fp8' (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
2K
1K last 30d - active
Likes
0
Model age
6w ago
created 2026-08-26
Downloads over time
Now2.5K→from0↑0%
09321.9K2.8K0 on Aug 262.5K on Oct 11AugSepOct
Aug 26 → Oct 11 · 47 snapshots · spans 46 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 ko
Quantizations
IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf qwen3.8 qwen3.5 multimodal image-text-to-text reasoning tool-calling long-context uncensored abliterated obliteratus

Related

Total size
176 GB
Files
15
Quantizations
9
Registered
2026-08-26 15:02
Last updated on HF
2026-10-06 21:18

Files by quantization

Q8_0 2 files 27.6 GB
SuperQwen3.8-abliterated-Venice.Q8_0.gguf 27.1 GB ebfd6512 download
SuperQwen3.8-abliterated-Venice.mmproj-Q8_0.gguf 600 MB 5339462c download
Q6_K 1 file 20.9 GB
SuperQwen3.8-abliterated-Venice.Q6_K.gguf 20.9 GB 4d0ade05 download
Q5_K 2 files 35.9 GB
SuperQwen3.8-abliterated-Venice.Q5_K_M.gguf 18.2 GB 4fb6929d download
SuperQwen3.8-abliterated-Venice.Q5_K_S.gguf 17.7 GB 8c26b294 download
Q4_K 2 files 30.4 GB
SuperQwen3.8-abliterated-Venice.Q4_K_M.gguf 15.7 GB fd31a230 download
SuperQwen3.8-abliterated-Venice.Q4_K_S.gguf 14.7 GB 7d4549e7 download
IQ4 1 file 14.4 GB
SuperQwen3.8-abliterated-Venice.IQ4_XS.gguf 14.4 GB 0538d233 download
Q3_K 3 files 37.5 GB
SuperQwen3.8-abliterated-Venice.Q3_K_L.gguf 13.6 GB a97250c7 download
SuperQwen3.8-abliterated-Venice.Q3_K_M.gguf 12.6 GB 9d675281 download
SuperQwen3.8-abliterated-Venice.Q3_K_S.gguf 11.4 GB 313641c7 download
Q2_K 1 file 10.1 GB
SuperQwen3.8-abliterated-Venice.Q2_K.gguf 10.1 GB 6164917b download
F16 1 file 885 MB
SuperQwen3.8-abliterated-Venice.mmproj-f16.gguf 885 MB 6ea1e329 download
Auxiliary files 2 files 6.74 KB
README.md 4.24 KB 3b1225fd download
.gitattributes 2.50 KB 1ed261af download

README current version from Hugging Face


base_model: Jiunsong/SuperQwen3.8-abliterated-100-fp8
language:

  • en
  • ko
    library_name: transformers
    license: apache-2.0
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • qwen3.8
  • qwen3.5
  • multimodal
  • image-text-to-text
  • reasoning
  • tool-calling
  • long-context
  • uncensored
  • abliterated
  • obliteratus
  • fp8
  • w8a8
  • compressed-tensors
  • vllm
  • h100
  • h200
  • speculative-decoding

About

static quants of https://huggingface.co/Jiunsong/SuperQwen3.8-abliterated-100-fp8

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

weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.

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 11.0
GGUF Q3_K_S 12.4
GGUF Q3_K_M 13.6 lower quality
GGUF Q3_K_L 14.7
GGUF Q4_K_S 15.9 fast, recommended
GGUF Q4_K_M 16.9 fast, recommended
GGUF Q5_K_S 19.1
GGUF Q5_K_M 19.6
GGUF Q6_K 22.5 very good quality
GGUF Q8_0 29.1 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. 2026-10-06auto-patch README.mdcc9cbec4.5 KB
    Loading...
  2. 2026-08-27auto-patch README.md950da8a4.3 KB
    Loading...
  3. 2026-08-26auto-patch README.md693a2694.4 KB
    Loading...
  4. 2026-08-26auto-patch README.mdfeb066b4.2 KB
    Loading...
  5. 2026-08-26auto-patch README.md328a04f3.9 KB
    Loading...
  6. 2026-08-26uploaded from nico19bfbca9383 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