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

III111II1I1/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-GGUF

III111II1I1 Qwen 9B GGUF multimodal 262K 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/III111II1I1%2FQwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-GGUF"
Response includes
  • classification m3
  • files 5
  • hub_downloads_all_time 4,697
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=qwen&method=m3
Sibling qwen 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
5K
321 last 30d - cooling
Likes
0
Model age
7mo ago
created 2026-03-05
Downloads over time
Now4.8K→from827↑483%
6272.2K3.7K5.2K827 on Mar 44.8K on Oct 11MarAprMayJunJulAugSepOct
Mar 4 → Oct 11 · 71 snapshots · spans 221 days

Metadata

Quantizations
Q4_K
Tags
gguf qwen3_5 llama.cpp unsloth vision-language-model endpoints_compatible region:us conversational
Total size
5.24 GB
Files
5
Quantizations
3
Registered
2026-08-22 13:56
Last updated on HF
2026-03-05 09:02
Source huggingface.co/III111II1I1/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-GGUF ↗

Files by quantization

Q4_K 1 file 5.24 GB
Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED.Q4_K_M.gguf 5.24 GB a3ad4547 download
mmproj 1 file 879 MB
Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED.BF16-mmproj.gguf 879 MB e3310e08 download
Auxiliary files 3 files 6.13 KB
config.json 3.36 KB d7823bdd download
.gitattributes 1.69 KB dc405eeb download
README.md 1.07 KB d854ba31 download

README current version from Hugging Face

tags:

  • gguf
  • llama.cpp
  • unsloth
  • vision-language-model

DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED

Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-GGUF : GGUF

This model was finetuned and converted to GGUF format using Unsloth.

Example usage:

  • For text only LLMs: llama-cli -hf III111II1I1/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-GGUF --jinja
  • For multimodal models: llama-mtmd-cli -hf III111II1I1/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-GGUF --jinja

Available Model files:

  • Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED.Q4_K_M.gguf
  • Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED.BF16-mmproj.gguf
    This was trained 2x faster with Unsloth

README history 3 versions

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

  1. 2026-03-05Update README.md9a893181.1 KB
    Loading...
  2. 2026-03-05Update README.md59b3e031007 B
    Loading...
  3. 2026-03-05Add READMEc84a3a6940 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