Get the app
← back to catalog · registered 2026-08-22 13:56

Avesed/Qwopus3.6-27B-v2-abliterated-int4

Avesed 19B 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/Avesed%2FQwopus3.6-27B-v2-abliterated-int4"
Response includes
  • classification m1
  • files 19
  • hub_downloads_all_time 758
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=Avesed
All 3 models by Avesed
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
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)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
758
20 last 30d - cooling
Likes
0
Model age
4mo ago
created 2026-06-13
Downloads over time
Now765→from0↑0%
02815618420 on Jun 10765 on Oct 11765 on Oct 7JunJulAugSepOct
Jun 10 → Oct 11 · 57 snapshots · spans 123 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.

Avesed/Qwopus3.6-27B-v2-abliterated↓ 26 this lineage
Avesed/Qwopus3.6-27B-v2-abliterated-int4↓ 20

Metadata

Tags
transformers safetensors qwen3_5 image-text-to-text abliterated uncensored compressed-tensors int4 text-generation conversational base_model:Avesed/Qwopus3.6-27B-v2-abliterated base_model:quantized:Avesed/Qwopus3.6-27B-v2-abliterated

Related

Other by Avesed
Qwopus3.6-27B-v2-abliterated-GGUF 251 Qwopus3.6-27B-v2-abliterated 26
Same base model
mradermacher/Qwopus3.6-27B-v2-abliterated-i1-GGUF 895 mradermacher/Qwopus3.6-27B-v2-abliterated-GGUF 749 Avesed/Qwopus3.6-27B-v2-abliterated-GGUF 251
Total size
26.6 GB
Files
19
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-13 15:23
Source huggingface.co/Avesed/Qwopus3.6-27B-v2-abliterated-int4 ↗ Base model Avesed/Qwopus3.6-27B-v2-abliterated →

Files by quantization

Auxiliary files 19 files 26.6 GB
model-00004-of-00008.safetensors 3.70 GB f3905fce download
model-00005-of-00008.safetensors 3.70 GB 8fa1b496 download
model-00003-of-00008.safetensors 3.69 GB ba2b2c0d download
model-00006-of-00008.safetensors 3.68 GB 8c6e8fa0 download
model-00007-of-00008.safetensors 3.63 GB 4b5920ad download
model-00002-of-00008.safetensors 3.63 GB 888e774f download
model-00001-of-00008.safetensors 2.37 GB 02fb68a9 download
model-00008-of-00008.safetensors 1.41 GB b276ba69 download
model-mtp.safetensors 810 MB 9c18f89f download
tokenizer.json 19.1 MB 701e4d26 download
model.safetensors.index.json 162 KB d76fc305 download
config.json 23.9 KB 9214a411 download
chat_template.jinja 7.87 KB f7a7d1b0 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.30 KB c93df11f download
tokenizer_config.json 1.17 KB 8943d027 download
recipe.yaml 1.07 KB d796b2c6 download
README.md 1.02 KB 43db0dde download
generation_config.json 167 B 08f907ee download

README current version from Hugging Face

base_model:

  • Avesed/Qwopus3.6-27B-v2-abliterated
    pipeline_tag: text-generation
    library_name: transformers
    tags:
  • abliterated
  • uncensored
  • qwen3_5
  • compressed-tensors
  • int4

Qwopus3.6-27B-v2-abliterated-int4

int4 weight-only (W4A16) quantization of Avesed/Qwopus3.6-27B-v2-abliterated. Deployable with vLLM (compressed-tensors / Marlin), ~26 GB.

Recipe

  • AWQ activation smoothing + int4 weight quantization, group_size=32, symmetric, MSE observer
  • Quantized: self_attn + mlp Linear layers
  • Kept higher precision (ignored): linear_attn, vision tower, MTP head, embed_tokens, lm_head

Evaluation

Benchmark Score
HumanEval pass@1 95.1%
GSM8K 86.0%
MMLU-Pro 83.2%
Refusal rate 8%

MTP head

The Multi-Token-Prediction (mtp) head is included (for speculative decoding). Its residual-write matrices (self_attn.o_proj, mlp.down_proj) are abliterated with the same refusal direction as the main layers.

README history 3 versions

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

  1. 2026-06-13Update README.mdab103b31 KB
    Loading...
  2. 2026-06-13Upload README.md with huggingface_hub49736f21 KB
    Loading...
  3. 2026-06-13Upload folder using huggingface_hub7b686a3808 B
    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.

Get the app Browse the catalog
Open in Abliteration