← back to catalog · registered 2026-09-27 00:57

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

BARKEM 24B multimodal second-order
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/BARKEM%2FQwen3.8-27B-Uncensored-W4A16-CT"
Response includes
  • classification m-uncensored
  • files 22
  • hub_downloads_all_time 73
  • 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 · lifetime
73
Likes
1
Model age
8w ago
created 2026-09-27
Downloads over time
Now 378 → from 0 ↑ 0%
0139277416 0 on Sep 27 378 on Nov 22 SepOctNov
Sep 27 → Nov 22 · 57 snapshots · spans 56 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.

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
18.1 GB
Files
22
Quantizations
1
Registered
2026-09-27 00:57
Last updated on HF
2026-09-27 00:14

Files by quantization

Auxiliary files 22 files 18.1 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 2.37 GB da51fa48 download
model-00007-of-00007.safetensors 2.37 GB 6866cf8a download
model_extra_tensors.safetensors 810 MB 7a9fd4ee download
model-00005-of-00007.safetensors 667 MB 0994bb8d 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 194 KB e3a119c1 download
config.json 15.0 KB f083264c download
quantization_config.json 10.9 KB 78f6d624 download
chat_template.jinja 8.74 KB c0c686f9 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.28 KB 3e1f70f1 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 compressed-tensors

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.
  • Size: 19.5 GB. 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).

README history 1 version

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

  1. 2026-09-27 Upload folder using huggingface_hub 808ac25 1.3 KB
    Loading...
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.

Open in Abliteration