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

Felldude/Qwen3.5-4B-Uncensored-FP8

Felldude Qwen 3.6B 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/Felldude%2FQwen3.5-4B-Uncensored-FP8"
Response includes
  • classification m-uncensored
  • files 12
  • hub_downloads_all_time 1,164
  • author_summary 14 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
1K
156 last 30d - stable
Likes
4
Model age
3mo ago
created 2026-07-02
Downloads over time
Now1.2K→from5↑24,440%
04508991.3K5 on Jul 11.2K on Oct 111.2K on Oct 10JulAugSepOct
Jul 1 → Oct 11 · 54 snapshots · spans 102 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.

Variants by this author 2 formats · 239 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3_5 image-text-to-text fp32 qwen uncensored caption conversational base_model:Qwen/Qwen3.5-4B-Base base_model:finetune:Qwen/Qwen3.5-4B-Base license:apache-2.0

Related

Total size
5.35 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-02 14:39

Files by quantization

Auxiliary files 12 files 5.38 GB
model.safetensors 5.35 GB 8889386b download
tokenizer.json 12.2 MB 5f9e4d49 download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
tokenizer_config.json 16.3 KB eda48d3e download
chat_template.jinja 7.57 KB a585dec8 download
config.json 3.09 KB 557d961b download
combine.py 1.75 KB 6e17686f download
README.md 1.68 KB dd5adf86 download
.gitattributes 1.53 KB 52373fe2 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download

README current version from Hugging Face


library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.4-9B/blob/main/LICENSE
pipeline_tag: image-text-to-text
base_model:

  • Qwen/Qwen3.5-4B-Base
    tags:
  • fp32
  • qwen
  • uncensored
  • caption

Qwen3.5-4B

USE FP32 version for quantization or conversion to BF16/FP16

[!Note]>
This model was trained in FP32 with Adam on Vision, Chain of Thought and Reasoning.
This model shows a massive increase in uncensored and unfiltered results using with THINK ON or with THINK OFF
In testing with think mode off 98% of results where uncensored. With THINK on the results are less consistent but far more unique.

Qwen3.5 Highlights

Qwen3.5 features the following enhancement:

  • Unified Vision-Language Foundation: Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.

  • Efficient Hybrid Architecture: Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead.

  • Scalable RL Generalization: Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability.

  • Global Linguistic Coverage: Expanded support to 201 languages and dialects, enabling inclusive, worldwide deployment with nuanced cultural and regional understanding.

  • Next-Generation Training Infrastructure: Near-100% multimodal training efficiency compared to text-only training and asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration.

README history 3 versions

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

  1. 2026-07-02Update README.mdd50344b1.7 KB
    Loading...
  2. 2026-07-02Update README.mdc8ca5e81.7 KB
    Loading...
  3. 2026-07-02initial commitdd801ed28 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