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

mradermacher/Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking-i1-GGUF

mradermacher Gemma 4B GGUF 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%2FGemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking-i1-GGUF"
Response includes
  • classification m3
  • files 27
  • hub_downloads_all_time 6,106
  • author_summary 3324 models
  • readme_text full
Try next
GET/models?author=mradermacher
All 3324 models by mradermacher
 GET/models?family=gemma&method=m3
Sibling gemma models · same method
 GET/methods/m3
What "m3" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
M1 Direct removal →
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
How we label → About M3 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
6K
936 last 30d - stable
Likes
2
Model age
8mo ago
created 2026-02-02

Training 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.

TeichAI/glm-4.7-2000x
Downloads over time
Now6.3K→from2K↑211%
1.8K3.5K5.1K6.7K2K on Feb 46.3K on Oct 11FebAprJunAugOct
Feb 4 → Oct 11 · 76 snapshots · spans 249 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.

DavidAU/Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking↓ 53 this lineage
mradermacher/Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking-i1-GGUF↓ 936

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
IQ1 IQ2 IQ3 IQ4 Q2_K Q3_K Q4 Q4_K Q5_K Q6_K
Tags
transformers gguf uncensored heretic abliterated unsloth finetune All use cases bfloat16 creative creative writing fiction writing

Related

Other by mradermacher
Ornith-1.5-9B-uncensored-GGUF 1.5M Qwen3-VL-8B-Instruct-abliterated-GGUF 667K Qwen3.8-Flash-Next-Uncensored-i1-GGUF 153K gemma-4-26B-A4B-it-ultra-uncensored-heretic-i1-GGUF 138K Qwen3.8-9B-heretic-uncensored-GGUF 106K
Same base model
mradermacher/Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking-GGUF 807
Total size
45.0 GB
Files
27
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2026-02-02 23:43
Source huggingface.co/mradermacher/Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking-i1-GGUF ↗ Base model DavidAU/Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking →

Files by quantization

Q6_K 1 file 2.97 GB
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-Q6_K.gguf 2.97 GB 108abc50 download
Q5_K 2 files 5.21 GB
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-Q5_K_M.gguf 2.64 GB 9475dadb download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-Q5_K_S.gguf 2.57 GB 462d4f38 download
Q4 2 files 4.60 GB
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-Q4_1.gguf 2.39 GB 84e2bc91 download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-Q4_0.gguf 2.21 GB 296fd514 download
Q4_K 2 files 4.53 GB
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-Q4_K_M.gguf 2.32 GB a3debb22 download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-Q4_K_S.gguf 2.21 GB 8c07352b download
IQ4 2 files 4.31 GB
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-IQ4_NL.gguf 2.20 GB d43d4dfb download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-IQ4_XS.gguf 2.11 GB bf8a40a1 download
Q3_K 3 files 5.84 GB
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-Q3_K_L.gguf 2.08 GB 9527700c download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-Q3_K_M.gguf 1.95 GB 96f38531 download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-Q3_K_S.gguf 1.80 GB eb68a5a6 download
IQ3 4 files 6.96 GB
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-IQ3_M.gguf 1.85 GB afb0f78e download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-IQ3_S.gguf 1.80 GB ced3431f download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-IQ3_XS.gguf 1.74 GB b5c587a3 download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-IQ3_XXS.gguf 1.57 GB bb22c76f download
Q2_K 2 files 3.13 GB
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-Q2_K.gguf 1.61 GB 969885c0 download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-Q2_K_S.gguf 1.52 GB 1174233e download
IQ2 4 files 5.31 GB
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-IQ2_M.gguf 1.43 GB fe69b882 download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-IQ2_S.gguf 1.35 GB b2c7b1dd download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-IQ2_XS.gguf 1.31 GB bd40ced0 download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-IQ2_XXS.gguf 1.22 GB 4d55ff8b download
IQ1 2 files 2.17 GB
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-IQ1_M.gguf 1.12 GB 56997899 download
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.i1-IQ1_S.gguf 1.06 GB 6a303189 download
Auxiliary files 3 files 3.30 MB
Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking.imatrix.gguf 3.29 MB cfa8122d download
README.md 8.60 KB 478d321d download
.gitattributes 4.16 KB 8656a4df download

README current version from Hugging Face

base_model: DavidAU/Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking
datasets:

  • TeichAI/glm-4.7-2000x
    language:
  • en
    library_name: transformers
    license: apache-2.0
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • uncensored
  • heretic
  • abliterated
  • unsloth
  • finetune
  • All use cases
  • bfloat16
  • creative
  • creative writing
  • fiction writing
  • plot generation
  • sub-plot generation
  • fiction writing
  • story generation
  • scene continue
  • storytelling
  • fiction story
  • science fiction
  • romance
  • all genres
  • story
  • writing
  • vivid prosing
  • vivid writing
  • fiction

About

weighted/imatrix quants of https://huggingface.co/DavidAU/Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking

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

static quants are available at https://huggingface.co/mradermacher/Gemma-3-4B-VL-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking-GGUF

This is a vision model - mmproj files (if any) will be in the static repository.

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 0.1 imatrix file (for creating your own quants)
GGUF i1-IQ1_S 1.2 for the desperate
GGUF i1-IQ1_M 1.3 mostly desperate
GGUF i1-IQ2_XXS 1.4
GGUF i1-IQ2_XS 1.5
GGUF i1-IQ2_S 1.5
GGUF i1-IQ2_M 1.6
GGUF i1-Q2_K_S 1.7 very low quality
GGUF i1-IQ3_XXS 1.8 lower quality
GGUF i1-Q2_K 1.8 IQ3_XXS probably better
GGUF i1-IQ3_XS 2.0
GGUF i1-IQ3_S 2.0 beats Q3_K*
GGUF i1-Q3_K_S 2.0 IQ3_XS probably better
GGUF i1-IQ3_M 2.1
GGUF i1-Q3_K_M 2.2 IQ3_S probably better
GGUF i1-Q3_K_L 2.3 IQ3_M probably better
GGUF i1-IQ4_XS 2.4
GGUF i1-IQ4_NL 2.5 prefer IQ4_XS
GGUF i1-Q4_0 2.5 fast, low quality
GGUF i1-Q4_K_S 2.5 optimal size/speed/quality
GGUF i1-Q4_K_M 2.6 fast, recommended
GGUF i1-Q4_1 2.7
GGUF i1-Q5_K_S 2.9
GGUF i1-Q5_K_M 2.9
GGUF i1-Q6_K 3.3 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 4 versions

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

  1. 2026-02-02auto-patch README.mdc5bbb608.6 KB
    Loading...
  2. 2026-02-02auto-patch README.md58f03588.3 KB
    Loading...
  3. 2026-02-02auto-patch README.mdd9eb7992.8 KB
    Loading...
  4. 2026-02-02uploaded from nico1b2866bb512 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.

Get the app Browse the catalog
Open in Abliteration