← back to catalog · registered 2026-09-14 09:56

inter521/Qwen3.8-27B-Uncensored-Aggressive-W4A16-AWQ

inter521 27B multimodal second-order
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals — repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-09-14

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
safetensors qwen3_5 uncensored abliterated qwen3 awq w4a16 compressed-tensors image-text-to-text conversational base_model:philbert440/Qwen3.8-27B-Uncensored-Aggressive base_model:quantized:philbert440/Qwen3.8-27B-Uncensored-Aggressive

Related

Total size
18.2 GB
Files
14
Quantizations
1
Registered
2026-09-14 09:56
Last updated on HF
2026-09-14 09:19

Files by quantization

Auxiliary files 14 files 18.2 GB
model.safetensors 17.4 GB 60b39473 download
model-mtp.safetensors 810 MB 90fa0e3e download
tokenizer.json 12.2 MB 0997f410 download
model.safetensors.index.json 201 KB f89faa40 download
config.json 20.4 KB f1640044 download
tokenizer_config.json 17.5 KB 5de744b3 download
recipe.yaml 11.2 KB 13381849 download
chat_template.jinja 8.74 KB c0c686f9 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.22 KB a3d49f4e download
processor_config.json 1.16 KB 33818c7f download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 214 B 8a2e2eff download

README current version from Hugging Face


license: apache-2.0
base_model: philbert440/Qwen3.8-27B-Uncensored-Aggressive
tags:

  • uncensored
  • abliterated
  • qwen3
  • awq
  • w4a16
  • compressed-tensors
    pipeline_tag: image-text-to-text

Qwen3.8-27B-Uncensored-Aggressive — W4A16 AWQ

4-bit weight (W4A16) AWQ quant of Qwen3.8-27B-Uncensored-Aggressive (α=1.15 recipe update),
in compressed-tensors format. Vision tower and the grafted MTP head are preserved.

About this update (α=1.15)

Recipe update to the Aggressive line: the previous build ablated at α≈1.24, which a larger benchmark
sweep showed over-ablates past the ~1.15 quality peak. This build uses α=1.15 — more open and
better on every measured axis.

Evaluation (bf16 parent, larger-sample, thinking mode, Claude-judged)

openness ↑ confab ↓ factual ↑ gsm8k ↑
stock base (censored) 0.08 0.75 1.00 0.85
Aggressive (α=1.15) 0.88 0.725 1.00 0.85
previous Aggressive (α≈1.24) 0.80 0.80 1.00 0.817

Quant: AWQ, group size 128, asymmetric, MSE observer, 256 Magpie-CoT calibration samples @1024 tokens.

Note

Uncensored / de-refused. Use responsibly and in compliance with applicable law.

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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.