← back to catalog · registered 2026-09-20 01:56

sjoe1244/gemma-4-31B-it-uncensored-heretic-exl3-3.00bpw-h4

sjoe1244 Gemma 31B multimodal second-order
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/sjoe1244%2Fgemma-4-31B-it-uncensored-heretic-exl3-3.00bpw-h4"
Response includes
  • classification m3
  • files 12
  • benchmarks 11 entries
  • author_summary 4 models
  • readme_text full
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
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-09-20

Benchmarks

Benchmark Score Source
Entertainment 2.7 UGI
Hazardous 4.7 UGI
Natural Intelligence 34.73 UGI
Political lean -18.5% UGI
Sensitive-Info 33.23 UGI
SocPol 3 UGI
UGI 53.82 UGI
Willingness (10) 9.5 UGI
W10-Adherence 10 UGI
W10-Direct 9 UGI
Writing 38.26 UGI

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
apache-2.0
Tags
safetensors gemma4 exl3 exllamav3 heretic uncensored vision base_model:llmfan46/gemma-4-31B-it-uncensored-heretic base_model:quantized:llmfan46/gemma-4-31B-it-uncensored-heretic license:apache-2.0 3-bit region:us

Related

Total size
14.0 GB
Files
12
Quantizations
1
Registered
2026-09-20 01:56
Last updated on HF
2026-09-20 01:26

Files by quantization

Auxiliary files 12 files 14.0 GB
model-00001-of-00002.safetensors 7.92 GB 0c58aa2e download
model-00002-of-00002.safetensors 6.05 GB 8098fd2d download
tokenizer.json 30.7 MB a2619fe1 download
quantization_config.json 648 KB 9b6553fd download
model.safetensors.index.json 302 KB 261eb726 download
chat_template.jinja 22.5 KB 4486ce43 download
config.json 5.64 KB ffcdcdd3 download
README.md 4.57 KB b5c38279 download
tokenizer_config.json 2.05 KB 375b25dc download
processor_config.json 1.65 KB 5465974d download
.gitattributes 1.53 KB 52373fe2 download
generation_config.json 217 B ed42ae71 download

README current version from Hugging Face


license: apache-2.0
base_model: llmfan46/gemma-4-31B-it-uncensored-heretic
base_model_relation: quantized
tags:

  • exl3
  • exllamav3
  • gemma4
  • heretic
  • uncensored
  • vision
    inference: false

gemma-4-31B-it-uncensored-heretic EXL3 3.00bpw h4

EXL3 export of llmfan46/gemma-4-31B-it-uncensored-heretic
for ExLlamaV3 / TabbyAPI. Vision tower included, quantized to 6 bpw.

Load with ExLlamaV3 or TabbyAPI's exllamav3 loader. This will not load in
Transformers, vLLM or llama.cpp.

This is the 4-bit-head companion to
-h6.
Same 3.0 bpw weights; the head and the vision tower are smaller. See
Differences from h6.

Quantization

From quantization_config.json:

Method EXL3
ExLlamaV3 1.5.0
Weights 3.0 bpw
Head 4 bits
Vision 6 bpw
Codebook mul1
Output scales always
Calibration 250 rows x 2048 cols

830 language-model modules at 3 bpw, lm_head at 4 bits, 354 vision modules at
6 bpw. embed_tokens is carried unchanged in BF16 (2.625 GiB) — ExLlamaV3 keeps
it in system RAM rather than VRAM.

config.json carries an audio_config, but the checkpoint has no audio tensors
— neither does the source or google/gemma-4-31B-it. This is an image+text model.

Converted on an RTX 4090 on 2026-09-19 from the BF16 source (62.5 GB).

Differences from h6

h6 this (h4)
ExLlamaV3 1.4.2 1.5.0
lm_head 6 bits, 0.985 GiB 4 bits, 0.657 GiB
Vision tower BF16, 1.061 GiB 6 bpw, 0.430 GiB
Total 14.927 GiB 13.961 GiB

The language-model layers are the same size in both, 10.245 GiB — same 3.0 bpw
over the same shapes. Only the head and the vision tower changed size.

The vision difference is not a choice: ExLlamaV3 1.4.2 could not quantize Gemma 4's
vision tower at all, so h6 stores it at BF16. 1.5.0 can.

Size

File Bytes
model-00001-of-00002.safetensors 8,498,844,777
model-00002-of-00002.safetensors 6,492,009,964
Total 14,990,854,741 (13.961 GiB)

Component breakdown, summed from the safetensors headers:

GiB
Language-model layers 10.245
embed_tokens (BF16, host RAM) 2.625
lm_head 0.657
Vision tower 0.430

Measured VRAM

Vision disabled, cache_mode: 3,3, real prefills at ~95% of the window — not
just successful loads.

RTX 4090, 24 GB (chunk_size: 128, max_batch_size: 2):

max_seq_len prefill peak
98,304 17,435 MiB
131,072 17,995 MiB
163,840 19,573 MiB
196,608 20,133 MiB
262,144 21,253 MiB

262,144 was the top of the sweep, not a limit — 3.3 GB was still free.

RTX 5080, 16 GB (chunk_size: 256, max_batch_size: 1):

max_seq_len prefill peak
61,440 15,021 MiB
73,728 15,741 MiB
81,920 15,837 MiB
90,112 fails mid-prefill

These are single-prefill verifications. A window that survives one clean prefill
can still OOM under sustained traffic, so run below the number in the table.

Only 10 of Gemma 4's 60 layers hold a per-token K/V cache — the other 50 are
sliding-window with fixed-size state — so at 3,3 context costs about
17.9 KiB/token, far less than the layer count suggests. On a card near its limit
the prefill working set, not the cache, is what binds.

Vision

The tower costs 454 MiB of VRAM. Setting EXL3_VISION_PINNED=1 holds it in
pinned host memory instead, cutting that to 54 MiB (measured at 61,440 on a
5080). Nothing else offloads — that flag applies to the vision component only.

Serving

TabbyAPI, as run here on a 4090:

max_seq_len: 98304
cache_size: 98304
cache_mode: 3,3
chunk_size: 128
gpu_split_auto: true
prompt_template: gemma4

chat_template.jinja is a separate file — Gemma 4 does not put the template in
tokenizer_config.json.

Quality

Not evaluated. The numbers above are memory and context measurements; no
benchmark or side-by-side against h6 has been run. 3.0 bpw with a 4-bit head is
an aggressive quant chosen to fit long context on one card, and a 4-bit head is
a further reduction on top of an already lossy export. If you have the VRAM,
prefer a higher-bpw build.

Credit and license

Apache 2.0, matching google/gemma-4-31B-it and the source model.

Decensoring credit belongs to llmfan46 — this
repo is only the EXL3 export. Quantization by
ExLlamaV3.

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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.