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

tbhrc/qwen3_5_9b_claude_4_6_highiq_instruct_heretic_uncensored_mxfp8

tbhrc Qwen 9.0B multimodal 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/tbhrc%2Fqwen3_5_9b_claude_4_6_highiq_instruct_heretic_uncensored_mxfp8"
Response includes
  • classification m3
  • files 14
  • hub_downloads_all_time 261
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=tbhrc
All 2 models by tbhrc
 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
261
160 last 30d - active
Likes
0
Model age
7w ago
created 2026-08-22
Downloads over time
Now316→from5↑6,220%
01162313475 on Aug 19316 on Oct 11AugSepOct
Aug 19 → Oct 11 · 48 snapshots · spans 53 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/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED↓ 148,058 this lineage
tbhrc/qwen3_5_9b_claude_4_6_highiq_instruct_heretic_uncensored_mxfp8↓ 160

Metadata

License
apache-2.0
Languages
en zh ru es fr it ja ko af de ar tr is pl sw sv nl he id uk fa pa pt ms fi el
Tags
mlx safetensors qwen3_5 heretic uncensored unrestricted decensored abliterated mxfp8 image-text-to-text conversational en

Related

Other by tbhrc
gemma_4_e4b_it_claude_opus_4_5_heretic_uncensored_thinking_mxfp8 276
Same base model
mradermacher/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-GGUF 10K TheCluster/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-MLX-mxfp8 7K mradermacher/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-i1-GGUF 2K enet45/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-mlx-4Bit 810 lainlives/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-GGUF 704
Total size
9.45 GB
Files
14
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-22 02:22
Source huggingface.co/tbhrc/qwen3_5_9b_claude_4_6_highiq_instruct_heretic_uncensored_mxfp8 ↗ Base model DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED →

Files by quantization

Auxiliary files 14 files 9.47 GB
model-00001-of-00002.safetensors 4.99 GB 1e7e5a3b download
model-00002-of-00002.safetensors 4.46 GB 790eda0c download
tokenizer.json 19.1 MB 87a7830d download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 103 KB 78949805 download
chat_template.jinja 7.61 KB 04dbb310 download
config.json 3.46 KB 1c88d7ca download
README.md 1.84 KB 585ae0e5 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.27 KB 7ad6acdf download
tokenizer_config.json 1.11 KB a068e246 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 115 B affcdf18 download

README current version from Hugging Face

license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.5-9B/blob/main/LICENSE
base_model:

  • DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED
    library_name: mlx
    tags:
  • heretic
  • uncensored
  • unrestricted
  • decensored
  • abliterated
  • mxfp8
    pipeline_tag: image-text-to-text
    language:
  • en
  • zh
  • ru
  • es
  • fr
  • it
  • ja
  • ko
  • af
  • de
  • ar
  • tr
  • is
  • pl
  • sw
  • sv
  • nl
  • he
  • id
  • uk
  • fa
  • pa
  • pt
  • ms
  • fi
  • el
If you like my work, you can support me

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

Quant: MXFP8 (8.363 bpw)

Fully uncensored and fine-tuned (by DavidAU) using Claude 4.6 large distill dataset.

This version is INSTRUCT, with modified jinja template which put this model into "instruct only" mode.

The model weights were updated on April 14.

Abliteration metrics

Metric This model Original model (Qwen/Qwen3.5-9B)
KL divergence 0.0793 0 (by definition)
Refusals 6/100 100/100

Benchmarks:

         arc   arc/e boolq hswag obkqa piqa  wino

HERETIC verison (this model):
mxfp8    0.574,0.755,0.869,0.714,0.410,0.780,0.691

Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT
mxfp8    0.574,0.729,0.882,0.711,0.422,0.775,0.691

Qwen3.5-9B
mxfp8    0.417,0.458,0.623,0.634,0.338,0.737,0.639

Source

This model was converted to MLX format from DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED using mlx-vlm version 0.4.4.

README history 1 version

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

  1. 2026-08-22sync Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-MLX-mxfp8 from ...a47860a1.8 KB
    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