Get the app
← back to catalog · registered 2026-09-27 02:57

tangles/Qwen3.8-27B-Uncensored-NVFP4-v100-skinny

tangles 27B multimodal second-order 
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/tangles%2FQwen3.8-27B-Uncensored-NVFP4-v100-skinny"
Response includes
  • classification m-uncensored
  • files 18
  • author_summary 1 models
  • readme_text full
Try next
GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
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
How we label → About M-U →
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.

orcarouter/Qwen3.8-27B-Uncensored↓ 25,984 this lineage
tangles/Qwen3.8-27B-Uncensored-NVFP4-v100-skinny

Metadata

License
apache-2.0
Tags
Model Optimizer safetensors qwen3_5 modelopt qwen3.8 nvfp4 fp8 v100-skinny image-text-to-text conversational base_model:orcarouter/Qwen3.8-27B-Uncensored base_model:quantized:orcarouter/Qwen3.8-27B-Uncensored

Related

Same base model
bartowski/orcarouter_Qwen3.8-27B-Uncensored-GGUF 154K pyros-vault/Qwen3.8-27B-Uncensored-NInfer 49K xidisdg/qwen3.8_27b-uncensored-ninfer 32K RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-Uncensored 28K fleetml/Qwen3.8-27B-Uncensored-NVFP4-RTX5090 27K
Total size
20.4 GB
Files
18
Quantizations
1
Registered
2026-09-27 02:57
Last updated on HF
2026-09-27 02:48
Source huggingface.co/tangles/Qwen3.8-27B-Uncensored-NVFP4-v100-skinny ↗ Base model orcarouter/Qwen3.8-27B-Uncensored →

Files by quantization

Auxiliary files 18 files 20.4 GB
model-00002-of-00003.safetensors 9.30 GB 8a97ee60 download
model-00001-of-00003.safetensors 9.28 GB 8805f706 download
model-00003-of-00003.safetensors 1.83 GB f24924cc download
tokenizer.json 19.1 MB 06b95093 download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
.quant_summary.txt 307 KB 75a975ba download
model.safetensors.index.json 210 KB 146d8eb2 download
config.json 85.6 KB 05257e22 download
hf_quant_config.json 52.5 KB aae809c6 download
chat_template.jinja 8.74 KB c0c686f9 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.16 KB 33818c7f download
tokenizer_config.json 1.09 KB 77053000 download
README.md 1.02 KB dc10fd02 download
quantization-audit.json 532 B f8f64a67 download
preprocessor_config.json 390 B 2ea84a43 download
generation_config.json 214 B 3f25ead4 download

README current version from Hugging Face

pipeline_tag: image-text-to-text
base_model: orcarouter/Qwen3.8-27B-Uncensored
license: apache-2.0
library_name: Model Optimizer
tags:

  • modelopt
  • qwen3.8
  • nvfp4
  • fp8
  • v100-skinny

Qwen3.8-27B-Uncensored NVFP4/FP8 for v100-skinny

Mixed-precision quantization of
orcarouter/Qwen3.8-27B-Uncensored,
prepared for dnv2003/v100-skinny.

  • MLP gate_proj, up_proj, down_proj, and lm_head: NVFP4, group size 16
  • Full- and linear-attention projections: FP8
  • Vision tower and MTP head: BF16
  • Calibration: max-abs, 1,024 abisee/cnn_dailymail train samples, sequence length 512
  • NVIDIA Model Optimizer source revision:
    87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c

See quantization-audit.json and hf_quant_config.json for the complete
machine-readable layout.

This model has had safety alignment substantially removed. Use it only for
lawful, controlled research and add appropriate safeguards before deployment.

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