license: apache-2.0
language:
- en
pipeline_tag: image-text-to-text
library_name: transformers
DavidAU/Qwen3.8-27B-Cold-Fable-Fusion-GAIN-V1.1-732-Heretic-Uncensored-stage1
Your rig
guess connected
? Why do I need an app?
The browser can't see your hardware
For privacy reasons a browser tells us at most "≥ 8 GB RAM, 8 cores" - same reading whether you have 8 GB or 128 GB. It has no idea how much RAM is free right now, which apps are open, or whether you have a GPU.
The Abliteration app is integrated with your machine
It reads your exact RAM, GPU model and VRAM, free memory right now, and picks the sharpest quant that still fits. Every model page lights up precisely for your rig.
And you can chat with any model, right now
The app is a full local runtime - no API keys, no subscription, everything runs on your machine. Click any model on this site and start a conversation in seconds.
Get the free 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/DavidAU%2FQwen3.8-27B-Cold-Fable-Fusion-GAIN-V1.1-732-Heretic-Uncensored-stage1" Response includes
- classification m3
- files 3
- author_summary 213 models
- readme_text full
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
Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · 30-day
17
↑ 467% in 90 days
Likes
95
Model age
6w ago
created 2026-08-25
Downloads over time
Aug 26 → Sep 1 · 7 snapshots · spans 6 days
Metadata
Related
Files by quantization
README
Discussions
2026-09-29New MLX quantifization with bit bumps in the last 4 layers and other places as …
Loading...2026-09-26There has always been a problem with prematurely stopping the output.
Loading...2026-09-15DeepSWE benchmark?
Loading...2026-09-08Deep Research and higher quality tasks
Loading...2026-09-07Request: GGUF Release of the Pre-Heretic 732 Checkpoint
Loading...2026-09-05Can't load the model in Unsloth Desktop
Loading...2026-09-04Creative Writing usage experience
Loading...2026-09-04A positive comment.
Loading...2026-09-03VERSION: Sharing W4A16 model for 3090 users
Loading...2026-09-03Can you make a dflash2-draft-model for the main-model？
Loading...2026-09-02鹈鹕自行车测试
Loading...2026-09-01Access request so I can quantize it for oMLX
Loading...2026-09-01Drooling over the name updates
Loading...2026-08-31Refusals compared to FF711
Loading...2026-08-31Request for access
Loading...2026-08-29Need approval for the model
Loading...2026-08-29Hi I need to be approved, would share my experience on Twitter and tag you Da…
Loading...2026-08-29We are getting closer
Loading...2026-08-27Excited!!
Loading...2026-08-26Was this finetune done to retain the level of thinking of the base so we can ha…
Loading...2026-08-26大佬是否能出个AWQ版本啊
Loading...2026-08-26Concerns
Loading...2026-08-25GGUF Please
Loading...2026-08-25Truly wish Gemma4 would have the same treat
Loading...2026-08-25Sooo hyped!
Loading...