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

mradermacher/OpenAi-GPT-oss-36B-BrainStorm20x-uncensored-GGUF

mradermacher Gpt-oss 36B GGUF MoE second-order 131K 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%2FOpenAi-GPT-oss-36B-BrainStorm20x-uncensored-GGUF"
Response includes
  • classification m8
  • files 13
  • hub_downloads_all_time 5,850
  • author_summary 3334 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/OpenAi-GPT-oss-36B-BrainStorm20x-uncensored' (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
6K
556 last 30d - cooling
Likes
1
Model age
13mo ago
created 2025-08-30
Downloads over time
Now6K→from1.5K↑307%
1.2K3K4.7K6.5K1.5K on Sep 3, 20256K on Oct 13Sep '25Nov '25JanMarMayJulSep
Sep 3, 2025 → Oct 13 · 99 snapshots · spans 405 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 gpt_oss gpt-oss openai mxfp4 programming code generation code coding coder chat

Related

Total size
276 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2025-08-31 14:52

Files by quantization

Q8_0 1 file 36.2 GB
OpenAi-GPT-oss-36B-BrainStorm20x-uncensored.Q8_0.gguf 36.2 GB 12b5b74b download
Q6_K 1 file 36.1 GB
OpenAi-GPT-oss-36B-BrainStorm20x-uncensored.Q6_K.gguf 36.1 GB f33640b7 download
Q5_K 2 files 53.1 GB
OpenAi-GPT-oss-36B-BrainStorm20x-uncensored.Q5_K_M.gguf 27.4 GB c0b79e4d download
OpenAi-GPT-oss-36B-BrainStorm20x-uncensored.Q5_K_S.gguf 25.7 GB fa30baaf download
Q4_K 2 files 49.3 GB
OpenAi-GPT-oss-36B-BrainStorm20x-uncensored.Q4_K_M.gguf 25.6 GB 30b7d254 download
OpenAi-GPT-oss-36B-BrainStorm20x-uncensored.Q4_K_S.gguf 23.7 GB 80c8fd40 download
Q3_K 3 files 61.8 GB
OpenAi-GPT-oss-36B-BrainStorm20x-uncensored.Q3_K_L.gguf 21.5 GB caa2bcc7 download
OpenAi-GPT-oss-36B-BrainStorm20x-uncensored.Q3_K_M.gguf 20.9 GB e7a9bb9c download
OpenAi-GPT-oss-36B-BrainStorm20x-uncensored.Q3_K_S.gguf 19.4 GB 6e6929b4 download
IQ4 1 file 19.7 GB
OpenAi-GPT-oss-36B-BrainStorm20x-uncensored.IQ4_XS.gguf 19.7 GB 79e4df76 download
Q2_K 1 file 19.4 GB
OpenAi-GPT-oss-36B-BrainStorm20x-uncensored.Q2_K.gguf 19.4 GB 6f193ef1 download
Auxiliary files 2 files 6.83 KB
README.md 4.37 KB c9258dc9 download
.gitattributes 2.47 KB 8a768228 download

README current version from Hugging Face


base_model: DavidAU/OpenAi-GPT-oss-36B-BrainStorm20x-uncensored
language:

  • en
    library_name: transformers
    license: apache-2.0
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • gpt_oss
  • gpt-oss
  • openai
  • mxfp4
  • programming
  • code generation
  • code
  • coding
  • coder
  • chat
  • code
  • chat
  • reasoning
  • thinking
  • r1
  • cot
  • deepseek
  • 128k context
  • general usage
  • problem solving
  • brainstorming
  • solve riddles
  • general usage
  • openai
  • uncensored
  • abliterated
  • Neo
  • MOE
  • Mixture of Experts
  • 24 experts
  • Brainstorm 20x
  • not-for-all-audiences

About

static quants of https://huggingface.co/DavidAU/OpenAi-GPT-oss-36B-BrainStorm20x-uncensored

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

weighted/imatrix quants are available at https://huggingface.co/mradermacher/OpenAi-GPT-oss-36B-BrainStorm20x-uncensored-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 Q3_K_S 21.0
GGUF Q2_K 21.0
GGUF IQ4_XS 21.3
GGUF Q3_K_M 22.5 lower quality
GGUF Q3_K_L 23.2
GGUF Q4_K_S 25.5 fast, recommended
GGUF Q4_K_M 27.6 fast, recommended
GGUF Q5_K_S 27.7
GGUF Q5_K_M 29.5
GGUF Q6_K 38.9 very good quality
GGUF Q8_0 39.0 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 4 versions

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

  1. 2025-08-31auto-patch README.md1da93054.4 KB
    Loading...
  2. 2025-08-31auto-patch README.mddcd5ade3.8 KB
    Loading...
  3. 2025-08-31auto-patch README.mdbbd29773.1 KB
    Loading...
  4. 2025-08-30uploaded from rich1e47e7cc393 B
    Loading...

Discussions 1 thread

  1. 2025-09-08Model performanceopen1 💬#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