← back to catalog · registered 2026-09-27 13:57

BARKEM/Qwen3.8-27B-Uncensored-W4A16-CT-HQ

BARKEM 27B multimodal second-order
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/BARKEM%2FQwen3.8-27B-Uncensored-W4A16-CT-HQ"
Response includes
  • classification m-uncensored
  • files 23
  • author_summary 2 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
safetensors qwen3_5 compressed-tensors w4a16 auto-round mtp uncensored hyperqwen image-text-to-text conversational base_model:orcarouter/Qwen3.8-27B-Uncensored base_model:quantized:orcarouter/Qwen3.8-27B-Uncensored

Related

Total size
15.6 GB
Files
23
Quantizations
1
Registered
2026-09-27 13:57
Last updated on HF
2026-09-27 07:27

Files by quantization

Auxiliary files 23 files 15.6 GB
model-00004-of-00007.safetensors 3.00 GB 99b4552c download
model-00001-of-00007.safetensors 2.99 GB 1b9a5303 download
model-00002-of-00007.safetensors 2.98 GB 6dabad06 download
model-00003-of-00007.safetensors 2.98 GB e3a913e0 download
model-00006-of-00007.safetensors 1.20 GB 560ddce0 download
model-00007-of-00007.safetensors 1.20 GB ce55d80e download
model-00005-of-00007.safetensors 667 MB 0994bb8d download
model_extra_tensors.safetensors 615 MB bbc9de9c download
mtp_draft_vocab_ids.pt 322 KB 8af90286 download
tokenizer.json 19.1 MB 06b95093 download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
model.safetensors.index.json 195 KB 1f1321de download
config.json 16.7 KB 13757880 download
quantization_config.json 10.9 KB 78f6d624 download
chat_template.jinja 9.34 KB 5358d6fd download
.gitattributes 1.83 KB 05e0f978 download
README.md 1.58 KB 555cbb6f download
processor_config.json 1.19 KB 43c4343e download
tokenizer_config.json 1.14 KB 1d134cd2 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 214 B c53835dc download

README current version from Hugging Face


license: apache-2.0
base_model:

  • orcarouter/Qwen3.8-27B-Uncensored
    tags:
  • compressed-tensors
  • w4a16
  • auto-round
  • qwen3_5
  • mtp
  • uncensored
  • hyperqwen
    pipeline_tag: image-text-to-text

Qwen3.8-27B Uncensored (orcarouter), W4A16, HyperQwen-prepared

A 4-bit weight-only quant of orcarouter/Qwen3.8-27B-Uncensored, an abliteration of the official Qwen3.8-27B. It is quantized the way dbirks/Qwen3.8-27B-W4A16-AutoRound is, so HyperQwen's prep and kernels apply and plain vLLM loads it with Marlin.

  • Format: compressed-tensors pack-quantized, int4, group 128, symmetric.
  • Quantizer: Intel AutoRound 0.15.0, 128 samples of NeelNanda/pile-10k at 2048 tokens, 200 iterations, seed 42.
  • Kept in BF16: GatedDeltaNet in_proj_a / in_proj_b, the vision tower, the MTP head and lm_head.
  • MTP head included (15 tensors), so --speculative-config '{"method":"mtp","num_speculative_tokens":3}' works.
  • Already prepared for HyperQwen: int8 lm_head, embeddings and MTP module, plus the 40k-token MTP draft head, so a server can start without running the prep step. The chat template renders the reasoning-effort line at the end of the prompt, so changing effort does not break the prefix cache.
  • Size: 19.5 GB before prep. Quantized in 34 minutes on one RTX 5090.

The refusal-removal results and benchmarks are on the source model card. Credit for the abliteration goes to orcarouter, and for the base model to the Qwen team (Apache 2.0).

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.