← back to catalog · registered 2026-11-15 13:03

mradermacher/occamy-1.0-abliterated-safetensors-i1-GGUF

mradermacher GGUF second-order
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%2Foccamy-1.0-abliterated-safetensors-i1-GGUF"
Response includes
  • classification m8
  • files 19
  • author_summary 3602 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='977895k/occamy-1.0-abliterated-safetensors' (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 · 30-day
7K
Likes
0
Model age
6d ago
created 2026-11-15
Downloads over time
Now 7K → from 0 ↑ 0%
02.6K5.1K7.7K 0 on Nov 15 7K on Nov 22 Nov
Nov 15 → Nov 22 · 8 snapshots · spans 7 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 · 9K downloads combined

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

Metadata

Languages
en
Quantizations
IQ1 IQ2 IQ3 IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K
Tags
transformers gguf en base_model:977895k/occamy-1.0-abliterated-safetensors base_model:quantized:977895k/occamy-1.0-abliterated-safetensors endpoints_compatible region:us imatrix conversational

Related

Total size
239 GB
Files
19
Quantizations
11
Registered
2026-11-15 13:03
Last updated on HF
2026-11-15 15:00

Files by quantization

Q6_K 1 file 26.6 GB
occamy-1.0-abliterated-safetensors.i1-Q6_K.gguf 26.6 GB bf62a0a9 download
Q5_K 1 file 22.3 GB
occamy-1.0-abliterated-safetensors.i1-Q5_K_S.gguf 22.3 GB 7f1f2844 download
Q4_K 2 files 38.2 GB
occamy-1.0-abliterated-safetensors.i1-Q4_K_M.gguf 19.7 GB 16a0bb0a download
occamy-1.0-abliterated-safetensors.i1-Q4_K_S.gguf 18.5 GB 6e5a4710 download
IQ4 1 file 17.4 GB
occamy-1.0-abliterated-safetensors.i1-IQ4_XS.gguf 17.4 GB 436c9e4d download
Q3_K 3 files 46.6 GB
occamy-1.0-abliterated-safetensors.i1-Q3_K_L.gguf 16.9 GB 1501577c download
occamy-1.0-abliterated-safetensors.i1-Q3_K_M.gguf 15.6 GB ba9a8d76 download
occamy-1.0-abliterated-safetensors.i1-Q3_K_S.gguf 14.1 GB 3dbf9b70 download
IQ3 2 files 27.1 GB
occamy-1.0-abliterated-safetensors.i1-IQ3_M.gguf 14.4 GB e2f5c9ef download
occamy-1.0-abliterated-safetensors.i1-IQ3_XXS.gguf 12.7 GB 0f284e92 download
Q2_K 2 files 23.4 GB
occamy-1.0-abliterated-safetensors.i1-Q2_K.gguf 12.1 GB 87fcf6b6 download
occamy-1.0-abliterated-safetensors.i1-Q2_K_S.gguf 11.3 GB ceedd4ad download
IQ2 3 files 29.5 GB
occamy-1.0-abliterated-safetensors.i1-IQ2_M.gguf 10.9 GB 93620f4e download
occamy-1.0-abliterated-safetensors.i1-IQ2_XS.gguf 9.79 GB 653495a6 download
occamy-1.0-abliterated-safetensors.i1-IQ2_XXS.gguf 8.85 GB 465d2b1b download
IQ1 1 file 7.67 GB
occamy-1.0-abliterated-safetensors.i1-IQ1_M.gguf 7.67 GB 30927589 download
Drafts and companions 1 file 367 MB
occamy-1.0-abliterated-safetensors.imatrix.gguf 367 MB 9e185fd2 download
Auxiliary files 2 files 7.71 KB
README.md 4.80 KB fa80f96c download
.gitattributes 2.90 KB e8cca80a download

README current version from Hugging Face


base_model: 977895k/occamy-1.0-abliterated-safetensors
language:

  • en
    library_name: transformers
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher

About

weighted/imatrix quants of https://huggingface.co/977895k/occamy-1.0-abliterated-safetensors

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

static quants are available at https://huggingface.co/mradermacher/occamy-1.0-abliterated-safetensors-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 imatrix 0.5 imatrix file (for creating your own quants)
GGUF i1-IQ1_M 8.3 mostly desperate
GGUF i1-IQ2_XXS 9.6
GGUF i1-IQ2_M 11.8
GGUF i1-Q2_K_S 12.3 very low quality
GGUF i1-Q2_K 13.0 IQ3_XXS probably better
GGUF i1-IQ3_XXS 13.7 lower quality
GGUF i1-Q3_K_S 15.3 IQ3_XS probably better
GGUF i1-IQ3_M 15.5
GGUF i1-Q3_K_M 16.9 IQ3_S probably better
GGUF i1-IQ4_XS 18.8
GGUF i1-Q4_K_S 20.0 optimal size/speed/quality
GGUF i1-Q4_K_M 21.3 fast, recommended
GGUF i1-Q6_K 28.6 practically like static Q6_K

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. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

README history 7 versions

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

  1. 2026-11-15 auto-patch README.md acbcd48 6.6 KB
    Loading...
  2. 2026-11-15 auto-patch README.md 058d721 6.4 KB
    Loading...
  3. 2026-11-15 auto-patch README.md 3766dd4 5.3 KB
    Loading...
  4. 2026-11-15 auto-patch README.md 28c0291 4.8 KB
    Loading...
  5. 2026-11-15 auto-patch README.md 9f317ae 3.5 KB
    Loading...
  6. 2026-11-15 auto-patch README.md 1125326 2.6 KB
    Loading...
  7. 2026-11-15 uploaded from marco 10bd144 488 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