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

Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-NVFP4

Name: Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-NVFP4
Author: Li101

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/Li101%2FQwen3.5-35B-A3B-Uncensored-Aggressive-NVFP4"

Response includes

classification m-uncensored
files 14
hub_downloads_all_time 1,656
author_summary 3 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.

Downloads · lifetime

360 last 30d - stable

Likes

Model age

6mo ago

created 2026-03-26

Downloads over time

Mar 25 → Oct 12 · 69 snapshots · spans 201 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.

Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-safetensors↓ 304 this lineage

Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-NVFP4↓ 360

Variants by this author 3 formats · 888 downloads combined

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

Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-NVFP4 (this) NVFP4 360
Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-safetensors safetensors 304
Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-FP8 FP8 224

Metadata

License

apache-2.0

Languages

en zh multilingual

Files by quantization

Auxiliary files 14 files 21.8 GB

model.safetensors-00001-of-00002.safetensors	20.9 GB	3c7e11b1	download
model.safetensors-00002-of-00002.safetensors	852 MB	3da73b37	download
model.safetensors.index.json	15.1 MB	e9858c42	download
tokenizer.json	12.2 MB	5f9e4d49	download
vocab.json	6.41 MB	0aa0ce06	download
config.json	28.4 KB	2572b8e9	download
tokenizer_config.json	16.3 KB	eda48d3e	download
config.json.llmc-original	13.7 KB	0f9ba339	download
chat_template.jinja	7.57 KB	a585dec8	download
README.md	2.12 KB	76ea9dbc	download
.gitattributes	1.60 KB	aa7aacd0	download
processor_config.json	1.27 KB	7ad6acdf	download
recipe.yaml	277 B	247e3d7e	download
generation_config.json	213 B	dff89e46	download

README current version from Hugging Face

license: apache-2.0
tags:

uncensored
qwen3.5
moe
safetensors
nvfp4
compressed-tensors
llm-compressor
vision
multimodal
language:
en
zh
multilingual
pipeline_tag: image-text-to-text
base_model: Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-safetensors
quantized_by: Li101

Qwen3.5-35B-A3B-Uncensored-Aggressive-NVFP4

NVFP4 quantized version of Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-safetensors, which is the "Aggressive" uncensoring variant of Qwen/Qwen3.5-35B-A3B. Includes full vision encoder weights (BF16, unquantized).

Quantization Details

Detail	Value
Method	NVFP4 (compressed-tensors)
Model size	~23 GB (vs 67 GB BF16)
Language model	NVFP4 quantized
Visual encoder	BF16 (unquantized, 333 tensors, 0.89 GB)
Excluded from quantization	lm_head, MoE gates, shared expert gates, linear attention layers, visual encoder

Calibration

Samples: 512 (256 from each dataset)
Datasets:
- HuggingFaceH4/ultrachat_200k (train_sft split) — length-filtered (longest conversations selected)
- nvidia/Nemotron-Post-Training-Dataset-v2 (chat split)
Max sequence length: 1024
All experts calibrated: moe_calibrate_all_experts=True

Usage with vLLM

Please use nightly vLLM for support.

vllm serve Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-NVFP4 \
    --kv-cache-dtype fp8 \
    --reasoning-parser qwen3 \
    --enable-auto-tool-choice \
    --tool-call-parser qwen3_coder

Specs

Same architecture and capabilities as Qwen/Qwen3.5-35B-A3B, including vision (image/video understanding).

Credits

Uncensoring by HauhauCS
Base model by Qwen
NVFP4 quantization and deployment by Li101

README history 1 version

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

2026-03-26Upload Qwen3.5-35B-A3B Uncensored Aggressive (NVFP4)d05ae7e2.1 KB
Loading...