← back to catalog · registered 2026-11-17 11:03

spale04/Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic

spale04 9B GGUF multimodal
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/spale04%2FQwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic"
Response includes
  • classification m3
  • files 18
  • author_summary 1 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
2K
Likes
0
Descendants
2
in 2 direct forks
Model age
5d ago
created 2026-11-17
Downloads over time
Now 1.6K → from 0 ↑ 0%
05961.2K1.8K 0 on Nov 17 1.6K on Nov 22 Nov
Nov 17 → Nov 22 · 6 snapshots · spans 5 days

Genealogy 2 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
Quantizations
Q8_0
Tags
transformers safetensors gguf qwen3_5 image-text-to-text merge della heretic abliterated uncensored decensored qwen3.5

Related

Total size
27.1 GB
Files
18
Quantizations
3
Registered
2026-11-17 11:03
Last updated on HF
2026-11-17 10:05

Files by quantization

Q8_0 1 file 9.11 GB
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic-Q8_0.gguf 9.11 GB f7080882 download
F16 1 file 876 MB
mmproj-Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic-F16.gguf 876 MB 74836df3 download
Auxiliary files 16 files 18.0 GB
model.safetensors-00003-of-00004.safetensors 5.00 GB cb2cf075 download
model.safetensors-00002-of-00004.safetensors 4.97 GB b4b40372 download
model.safetensors-00001-of-00004.safetensors 4.91 GB 85dc6b40 download
model.safetensors-00004-of-00004.safetensors 3.10 GB 499f9091 download
tokenizer.json 12.2 MB 5f9e4d49 download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
model.safetensors.index.json 77.8 KB e4c1cb7d download
tokenizer_config.json 16.3 KB eda48d3e download
LICENSE 11.3 KB f938136e download
README.md 10.3 KB 0553dab2 download
chat_template.jinja 7.57 KB a585dec8 download
config.json 3.05 KB 273ce437 download
.gitattributes 1.86 KB 89b118ec download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download

README current version from Hugging Face


license: apache-2.0
base_model:

  • Jackrong/Qwopus3.5-9B-v3
  • Goekdeniz-Guelmez/JOSIE-2-9B-OSS
    base_model_relation: merge
    pipeline_tag: image-text-to-text
    library_name: transformers
    tags:
  • gguf
  • merge
  • della
  • heretic
  • abliterated
  • uncensored
  • decensored
  • qwen3.5
  • qwen
  • llama.cpp
  • vision
  • reasoning

Qwopus-JOSIE Qwen3.5 9B, UNCENSORED Heretic edition

Two Qwen3.5-9B fine-tunes fused into one model, then decensored. 9 refusals in 100, and it knows more than the original.
Full weights and GGUF in one repo, for transformers, llama.cpp and LM Studio. Text and image input, with thinking mode.

spaleai.com
Follow on X
GitHub
Join the Discord

Refusals 9/100 MMLU-Pro 73.8, original 59.5 HumanEval 95.0 36 tokens per second Apache 2.0

Highlights

  • Two models in one. Qwopus3.5-9B-v3 for reasoning (70%) and JOSIE-2-9B-OSS (30%), fused with DELLA.
  • Knows more than the original. On MMLU-Pro it scores 73.8 against 59.5: 15 questions gained and 3 lost.
  • Answers instead of refusing. The original refused 99/100 prompts; this model refuses 9/100.
  • Thinks shorter. It uses about 29% fewer tokens per answer than the original, which left 27 of 84 MMLU-Pro answers unfinished at 12,000 tokens.
  • Sees images. Add the mmproj file and it takes images, like the original.
  • Transparent. Weaker spots are listed below too: instruction following and writing.

Quick start

One command with llama.cpp downloads the model and the image encoder:

llama-server -hf spale04/Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic:Q8_0 -ngl 99 -c 32768 --jinja --temp 1.0 --top-p 0.95 --top-k 20 --presence-penalty 1.5

Then open http://127.0.0.1:8080 in a browser.
With that context and the image encoder it uses about 11.6 GB on a 12 GB RTX 3060. Add -ctk q8_0 -ctv q8_0 for more room.
In LM Studio, search for spale04/Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.

About

This is a fusion of two fine-tunes of Qwen/Qwen3.5-9B: Qwopus3.5-9B-v3 and JOSIE-2-9B-OSS.
Their changes were combined with DELLA, and the refusals were then removed with Heretic 2.1.0 (Arbitrary-Rank Ablation).
Everything was made on a single RTX 3060 12 GB.

This model has had its refusals removed and is not safety-aligned. Add your own guardrails where they matter.

Files

File Size Use
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic-Q8_0.gguf 9.79 GB the text model, 8-bit, near lossless
mmproj-Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic-F16.gguf 0.92 GB image encoder, used together with the file above
model.safetensors-* 19.3 GB full bf16 weights for transformers, vLLM or further merging

Abliteration result

Measured by Heretic on 100 harmful and 100 harmless prompts, with the model loaded in 4-bit (NF4):

Fusion before Heretic This model
Refusals 100/100 6/100
KL divergence from the fusion 0 0.0126

Trial 98 of 100 was chosen, but only after two candidates got the full benchmark.
The stronger trial 57 (3/100 refusals, KL 0.024) was rejected: Heretic's KL test missed that it hurt long reasoning (HumanEval 90.0, MMLU-Pro 71.4).
A gentler trial on the Pareto front kept 12/100 refusals at KL 0.0082.

Benchmarks

All three models ran as Q8_0 GGUF in llama-server (b12422), with the same questions, seeds and settings.
Thinking was on, with temperature 1.0, top-p 0.95, top-k 20 and presence penalty 1.5 (temperature 0.6 and no penalty for code), and at most 12,000 tokens per answer.
An unfinished answer counts as wrong. ± is one standard error. HumanEval runs the generated code against the official tests.

Benchmark Questions Original Qwen3.5-9B Fusion, before Heretic This model
GSM8K 60 96.7 ± 2.3 96.7 ± 2.3 95.0 ± 2.8
MMLU-Pro 84 (6 per category) 59.5 ± 5.4 77.4 ± 4.6 73.8 ± 4.8
HumanEval pass@1 60 98.3 ± 1.7 95.0 ± 2.8 95.0 ± 2.8
IFEval, prompt-level strict 60 88.3 ± 4.1 85.0 ± 4.6 81.7 ± 5.0
Mean 85.7 88.5 86.4
Refusals (harmful_behaviors) 100 99 100* 9 ± 2.9
Writing, scored blind, 1–10 10 7.05 6.55 6.15
Mean tokens per answer (first 4 tests) 3,782 2,563 2,694

* Heretic's own count.

The one clear win is knowledge. On MMLU-Pro the fusion gained 15 questions against the original and lost 3. Part of that gain comes from shorter thinking: the original ran out of tokens on 27 of 84 questions, this model on 8.
Instruction following is the weak spot. On IFEval it lost 6 prompts and gained 2. That is within noise, but the trend is down. Writing is also a little weaker.
On HumanEval it lost 3 tasks and gained 1.

Speed

About 36 tokens/s for Q8_0 on an RTX 3060 12 GB in llama-server, with all layers on the GPU and one request at a time.

Usage

llama-server -m Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic-Q8_0.gguf --mmproj mmproj-Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic-F16.gguf -ngl 99 -c 32768 --jinja --temp 1.0 --top-p 0.95 --top-k 20 --presence-penalty 1.5

Thinking is on by default. For quick answers, turn it off with --reasoning off, or per request with "chat_template_kwargs": {"enable_thinking": false}.
For code, use temperature 0.6 and no presence penalty.

Set a context limit, because the model's default is 262,144 tokens.
The image encoder is unchanged from the original model; the fusion and Heretic only modify the language layers.

How it was made

  1. Choosing the recipe. Four fusions were compared on 54 questions on which the source models disagree:

    • TIES of Qwopus and a DeepSeek-V4-Pro distill
    • the original plus 0.6 × Qwopus
    • DELLA with Qwopus and a DeepSeek-V4-Pro distill
    • DELLA with Qwopus and JOSIE

    Qwopus + JOSIE won with 43 of 54. The others scored 41, 39 and 38. For comparison, Qwopus alone scored 37 and the original 31.

  2. Fusion. DELLA with density 0.5, epsilon 0.1, weights 0.7 / 0.3 and a weighted sum, on top of Qwen3.5-9B. It changes 152 language tensors.

  3. Heretic. heretic with quantization = "bnb_4bit", 100 trials and batch size 32.

  4. Picking a trial. Two Pareto-front trials got the full benchmark. Trial 98 won, and its LoRA was folded into the bf16 weights.

  5. Conversion. convert_hf_to_gguf.py --outtype q8_0, plus --mmproj for the image encoder.

Made by

Made by spale04 (SpaleAI) on a single RTX 3060. New models and experiments get posted on X first, and the Discord is the place for questions and feedback.

spaleai.com
Follow on X
GitHub
Join the Discord

Also from spale04:

If the model is useful to you, a like on this page helps other people find it.

License

Apache 2.0, the same as the base model Qwen/Qwen3.5-9B and Qwopus3.5-9B-v3 (Jackrong).
JOSIE-2-9B-OSS (Gökdeniz Gülmez) is MIT-licensed and keeps its credit here.
Refusal removal by Heretic (p-e-w).

README history 2 versions

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

  1. 2026-11-17 Rename to Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic fe3ca4b 10.3 KB
    Loading...
  2. 2026-11-17 Add files using upload-large-folder tool 380eb2c 10.2 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.

Open in Abliteration