← back to catalog · registered 2026-11-13 18:03

Luni/DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic-ComfyUI-W4A8

Luni Deepseek 4B second-order
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/Luni%2FDeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic-ComfyUI-W4A8"
Response includes
  • classification m3
  • files 2
  • author_summary 2 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
1
Model age
1w ago
created 2026-11-13
Downloads over time
Now 0 → from 0 ↑ 0%
0011 0 on Nov 13 0 on Nov 22 Nov
Nov 13 → Nov 22 · 10 snapshots · spans 9 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
apache-2.0
Tags
comfyui qwen3.5 w4a8 base_model:xtools-at/DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic base_model:finetune:xtools-at/DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic license:apache-2.0 region:us

Related

Total size
0 B
Files
2
Quantizations
1
Registered
2026-11-13 18:03
Last updated on HF
2026-11-13 20:26

Files by quantization

Auxiliary files 2 files 2.19 KB
.gitattributes 1.48 KB a6344aac download
README.md 722 B f6130397 download

README current version from Hugging Face


base_model:

  • xtools-at/DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic
    license: apache-2.0
    tags:
  • comfyui
  • qwen3.5
  • w4a8

DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic — ComfyUI W4A8

xtools-at/DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic as a single ComfyUI-native file, in the same format as Comfy-Org's qwen3.5_9b_w4a8_gptq.safetensors. Use in Load CLIP → Generate Text (prompt enhancers).

  • Language layers: W4A8 (int4 + fp8 group-16 scales, convrot 256); tied embeddings: int8 convrot; vision tower and MTP head: bf16.
  • MTP speculative decoding works (mtp: auto).

Put it in ComfyUI/models/text_encoders/.

README history 2 versions

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

  1. 2026-11-13 Upload README.md with huggingface_hub 1c6bdfc 764 B
    Loading...
  2. 2026-11-13 Upload README.md with huggingface_hub ca2cf45 722 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