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

mradermacher/Mistral-Medium-3.5-128B-Eschaton-Uncensored-GGUF

mradermacher Mistral 128B 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%2FMistral-Medium-3.5-128B-Eschaton-Uncensored-GGUF"
Response includes
  • classification m8
  • files 19
  • hub_downloads_all_time 8,111
  • 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='cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-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
8K
2K last 30d - stable
Likes
0
Model age
2mo ago
created 2026-07-25

Training datasets

1 of 1 in /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
Now9.6K→from652↑1,370%
2053.6K7.1K10.5K652 on Jul 299.6K on Oct 11JulAugSepOct
Jul 29 → Oct 11 · 51 snapshots · spans 74 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
other
Languages
en
Quantizations
IQ4 Q2_K Q3_K Q4_K Q5_K
Tags
transformers gguf peft lora qlora bitsandbytes mistral mistral3 mistral-medium multimodal reasoning eschaton-engine

Related

Total size
574 GB
Files
19
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-10-09 21:26

Files by quantization

Q5_K 2 files 163 GB
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q5_K_M.gguf 82.3 GB 586faee2 download
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q5_K_S.gguf 80.3 GB 68ce5768 download
Q4_K 2 files 136 GB
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q4_K_M.gguf 69.8 GB e5bd8e6b download
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q4_K_S.gguf 66.4 GB 3d94bac6 download
IQ4 1 file 63.0 GB
Mistral-Medium-3.5-128B-Eschaton-Uncensored.IQ4_XS.gguf 63.0 GB 0f6c3847 download
Q3_K 3 files 169 GB
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q3_K_L.gguf 61.5 GB 9b9a1d65 download
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q3_K_M.gguf 56.5 GB 0255877b download
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q3_K_S.gguf 50.6 GB 647f16ab download
Q2_K 1 file 43.4 GB
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q2_K.gguf 43.4 GB fb1e9ee1 download
Q8_0 1 file 2.03 KB
Mistral-Medium-3.5-128B-Eschaton-Uncensored.mmproj-Q8_0.gguf 2.03 KB e4068680 download
F16 1 file 2.03 KB
Mistral-Medium-3.5-128B-Eschaton-Uncensored.mmproj-f16.gguf 2.03 KB 1a82aebd download
Auxiliary files 8 files 219 GB
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q8_0.gguf.part1of3 42.0 GB 4c49d3ad download
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q8_0.gguf.part2of3 42.0 GB 2205f375 download
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q8_0.gguf.part3of3 39.7 GB a7c521a9 download
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q6_K.gguf.part1of3 32.0 GB 2645ce28 download
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q6_K.gguf.part2of3 32.0 GB 91d379cd download
Mistral-Medium-3.5-128B-Eschaton-Uncensored.Q6_K.gguf.part3of3 31.5 GB 5597a92a download
README.md 5.43 KB 2c4f9bdf download
.gitattributes 2.87 KB ab0c1f5f download

README current version from Hugging Face


base_model: cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored
datasets:

  • cloudbjorn/eschaton-uncensored
    language:
  • en
    library_name: transformers
    license: other
    license_link: https://huggingface.co/mistralai/Mistral-Medium-3.5-128B/blob/main/LICENSE
    license_name: modified-mit
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • transformers
  • peft
  • lora
  • qlora
  • bitsandbytes
  • mistral
  • mistral3
  • mistral-medium
  • multimodal
  • reasoning
  • eschaton-engine
  • eschaton-uncensored
  • uncensored

About

static quants of https://huggingface.co/cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-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/Mistral-Medium-3.5-128B-Eschaton-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 mmproj-Q8_0 0.1 multi-modal supplement
GGUF mmproj-f16 0.1 multi-modal supplement
GGUF Q2_K 46.7
GGUF Q3_K_S 54.5
GGUF Q3_K_M 60.7 lower quality
GGUF Q3_K_L 66.2
GGUF IQ4_XS 67.8
GGUF Q4_K_S 71.3 fast, recommended
GGUF Q4_K_M 75.0 fast, recommended
GGUF Q5_K_S 86.3
GGUF Q5_K_M 88.4
PART 1 PART 2 PART 3 Q6_K 102.7 very good quality
PART 1 PART 2 PART 3 Q8_0 133.0 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 5 versions

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

  1. 2026-10-09auto-patch README.md601fe735.7 KB
    Loading...
  2. 2026-07-26auto-patch README.md6c3b3cd5.4 KB
    Loading...
  3. 2026-07-25auto-patch README.md9520a8d5.5 KB
    Loading...
  4. 2026-07-25auto-patch README.md60cf0455.3 KB
    Loading...
  5. 2026-07-25uploaded from nico18b221cd397 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