← back to catalog · registered 2026-09-27 14:57

JaelTmls/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-OpenVINO-INT4

JaelTmls 9B multimodal second-order
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/JaelTmls%2FQwen3.5-9B-Uncensored-HauhauCS-Aggressive-OpenVINO-INT4"
Response includes
  • classification m-uncensored
  • files 26
  • author_summary 1 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 · 30-day
0
Likes
0
Model age
today
created 2026-09-27

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.

Metadata

License
apache-2.0
Tags
openvino qwen3_5 intel-npu int4 qwen3.5 uncensored optimum image-text-to-text conversational base_model:GitMylo/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-safetensors base_model:finetune:GitMylo/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-safetensors license:apache-2.0

Related

Total size
5.80 GB
Files
26
Quantizations
1
Registered
2026-09-27 14:57
Last updated on HF
2026-09-27 14:52

Files by quantization

Auxiliary files 26 files 5.82 GB
openvino_language_model.bin 4.27 GB 1def27ea download
openvino_text_embeddings_model.bin 970 MB fd80debc download
openvino_vision_embeddings_merger_model.bin 432 MB 8c660770 download
openvino_mtp_model.bin 143 MB 86f75a9a download
openvino_tokenizer.bin 9.18 MB 7f883a0f download
openvino_detokenizer.bin 3.65 MB 48fc2c6a download
openvino_vision_embeddings_pos_model.bin 2.54 MB 247b5afc download
openvino_vision_embeddings_model.bin 1.69 MB 66936c63 download
tokenizer.json 19.1 MB 87a7830d download
openvino_language_model.xml 4.46 MB 421b9d67 download
openvino_vision_embeddings_merger_model.xml 1.31 MB e5dc1a13 download
openvino_mtp_model.xml 206 KB 58580477 download
openvino_tokenizer.xml 34.2 KB 356687c0 download
openvino_detokenizer.xml 15.4 KB f91efb80 download
openvino_vision_embeddings_model.xml 8.71 KB 7507ead7 download
chat_template.jinja 7.72 KB 945efe1d download
openvino_text_embeddings_model.xml 5.97 KB fc43cda7 download
openvino_vision_embeddings_pos_model.xml 5.94 KB 003dc612 download
config.json 2.86 KB 8e597ab2 download
README.md 2.71 KB 56f20521 download
openvino_config.json 2.10 KB 42cd522a download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.33 KB 9e6a6794 download
tokenizer_config.json 1.14 KB 724d0f83 download
preprocessor_config.json 509 B 27468943 download
generation_config.json 121 B 0b5586c4 download

README current version from Hugging Face


library_name: openvino
base_model:

  • HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive
  • GitMylo/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-safetensors
    tags:
  • openvino
  • intel-npu
  • int4
  • qwen3.5
  • uncensored
  • optimum
    pipeline_tag: image-text-to-text
    license: apache-2.0

Qwen3.5-9B-Uncensored-HauhauCS-Aggressive — OpenVINO INT4 (Intel NPU Optimized)

This repository contains the OpenVINO™ Intermediate Representation (IR) model for Qwen3.5-9B-Uncensored-HauhauCS-Aggressive, optimized for Intel NPU (Neural Processing Unit, such as Intel® Core™ Ultra processors) as well as Intel CPU and GPU.

The model weights are compressed to INT4 Symmetric format using NNCF (Neural Network Compression Framework) via Optimum Intel, meeting Intel NPU hardware execution specifications.

Model Highlights

Requirements

pip install --upgrade openvino openvino-genai optimum-intel transformers

Inference on Intel NPU

1. Using OpenVINO GenAI (Recommended for low-latency NPU inference)

import openvino_genai as ov_genai

# Load model onto Intel NPU
pipe = ov_genai.VLMPipeline("JaelTmls/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-OpenVINO-INT4", device="NPU")

# For text-only generation:
prompt = "Explain quantum computing in simple terms."
response = pipe.generate(prompt, max_new_tokens=256)
print(response.texts[0])

(Note: If NPU device is not available, you can replace "NPU" with "GPU" or "CPU").

2. Using Optimum Intel

from optimum.intel.openvino import OVModelForVisualCausalLM
from transformers import AutoProcessor

model_id = "JaelTmls/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-OpenVINO-INT4"
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
model = OVModelForVisualCausalLM.from_pretrained(model_id, device="NPU")

# Run generation
inputs = processor("Hello!", return_tensors="pt")
output = model.generate(**inputs, max_new_tokens=100)
print(processor.decode(output[0], skip_special_tokens=True))

Quantization Details

  • Method: NNCF Weight Compression
  • Weight format: INT4 Symmetric
  • Group size: 128
  • Ratio: 1.0 (all linear layers quantized to 4-bit)
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.