← back to catalog · registered 2026-09-04 16:03

mradermacher/LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored-GGUF

mradermacher GGUF second-order 128K 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%2FLFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored-GGUF"
Response includes
  • classification m8
  • files 14
  • hub_downloads_all_time 1,029
  • author_summary 3365 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='Null-Guard/LFM2.5-230M-distilled-Gemini-3.8-Flash-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
1K
725 last 30d - active
Likes
0
Model age
6w ago
created 2026-09-04
Downloads over time
Now1.5K→from0↑0%
05481.1K1.6K0 on Sep 41.5K on Oct 20SepOct
Sep 4 → Oct 20 · 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.

Metadata

License
other
Languages
en zh
Quantizations
F16 IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf lfm2.5 distilled uncensored abliterated abliteration conversational text-generation-inference en zh base_model:Null-Guard/LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored

Related

Total size
2.05 GB
Files
14
Quantizations
9
Registered
2026-09-04 16:03
Last updated on HF
2026-09-04 15:51

Files by quantization

F16 1 file 440 MB
LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored.f16.gguf 440 MB 4681d8e4 download
Q8_0 1 file 235 MB
LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored.Q8_0.gguf 235 MB 5ef71fb6 download
Q6_K 1 file 182 MB
LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored.Q6_K.gguf 182 MB 883f246d download
Q5_K 2 files 325 MB
LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored.Q5_K_M.gguf 164 MB 3ece2a36 download
LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored.Q5_K_S.gguf 162 MB e64244e7 download
Q4_K 2 files 289 MB
LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored.Q4_K_M.gguf 146 MB 61518356 download
LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored.Q4_K_S.gguf 143 MB 87126041 download
IQ4 1 file 138 MB
LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored.IQ4_XS.gguf 138 MB e77fbf94 download
Q3_K 3 files 382 MB
LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored.Q3_K_L.gguf 133 MB bb5cf459 download
LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored.Q3_K_M.gguf 128 MB 0386f6b4 download
LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored.Q3_K_S.gguf 122 MB ceedc29d download
Q2_K 1 file 110 MB
LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored.Q2_K.gguf 110 MB 6fe62808 download
Auxiliary files 2 files 7.25 KB
README.md 4.63 KB 12948af7 download
.gitattributes 2.62 KB 00be6452 download

README current version from Hugging Face


base_model: Null-Guard/LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored
language:

  • en
  • zh
    library_name: transformers
    license: other
    license_link: https://huggingface.co/LiquidAI/LFM2.5-230M
    license_name: lfm2.5-license
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • lfm2.5
  • distilled
  • uncensored
  • abliterated
  • abliteration
  • conversational
  • text-generation-inference

About

static quants of https://huggingface.co/Null-Guard/LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored

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 Q2_K 0.2
GGUF Q3_K_S 0.2
GGUF Q3_K_M 0.2 lower quality
GGUF Q3_K_L 0.2
GGUF IQ4_XS 0.2
GGUF Q4_K_S 0.2 fast, recommended
GGUF Q4_K_M 0.3 fast, recommended
GGUF Q5_K_S 0.3
GGUF Q5_K_M 0.3
GGUF Q6_K 0.3 very good quality
GGUF Q8_0 0.3 fast, best quality
GGUF f16 0.6 16 bpw, overkill

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 2 versions

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

  1. 2026-09-04auto-patch README.mdda814594.6 KB
    Loading...
  2. 2026-09-04uploaded from leia14d6d2d403 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