Get the app
← back to catalog · registered 2026-11-03 23:02

AntGPU/Qwen3.8-27b-abliterated-vx_underground-v2-whiterabbit-GGUF

AntGPU 27B GGUF multimodal
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/AntGPU%2FQwen3.8-27b-abliterated-vx_underground-v2-whiterabbit-GGUF"
Response includes
  • classification m8
  • files 6
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=AntGPU
All 2 models by AntGPU
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
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=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
How we label → About M8 →
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
4
↑ 0% in 90 days
Likes
1
Model age
2w ago
created 2026-10-17
Downloads over time
Now4→from4↑0%
44554 on Nov 34 on Nov 4Nov
Nov 3 → Nov 4 · 2 snapshots · spans 1 day

Metadata

Quantizations
Q4_K Q5_K
Tags
gguf qwen3_5 llama.cpp llama-cpp unsloth vision-language-model endpoints_compatible region:us conversational

Related

Other by AntGPU
Qwen3.8-27b-abliterated-vx_underground-v2-GGUF 4
Total size
33.9 GB
Files
6
Quantizations
4
Registered
2026-11-03 23:02
Last updated on HF
2026-10-17 15:27
Source huggingface.co/AntGPU/Qwen3.8-27b-abliterated-vx_underground-v2-whiterabbit-GGUF ↗

Files by quantization

Q5_K 1 file 18.2 GB
Huihui-Qwen3.8-27B-abliterated.Q5_K_M.gguf 18.2 GB a41fc8b9 download
Q4_K 1 file 15.7 GB
Huihui-Qwen3.8-27B-abliterated.Q4_K_M.gguf 15.7 GB d7eac059 download
mmproj 1 file 888 MB
Huihui-Qwen3.8-27B-abliterated.BF16-mmproj.gguf 888 MB 49970548 download
Auxiliary files 3 files 6.55 KB
config.json 4.18 KB 57e5c372 download
.gitattributes 1.72 KB 660541b4 download
README.md 672 B cedaa094 download

README current version from Hugging Face

tags:

  • gguf
  • llama.cpp
  • llama-cpp
  • unsloth
  • vision-language-model

Qwen3.8-27b-abliterated-vx_underground-v2-whiterabbit-GGUF : GGUF

This model was converted to GGUF format using Unsloth.

Example usage:

  • For text only LLMs: llama-cli -hf AntGPU/Qwen3.8-27b-abliterated-vx_underground-v2-whiterabbit-GGUF --jinja
  • For multimodal models: llama-mtmd-cli -hf AntGPU/Qwen3.8-27b-abliterated-vx_underground-v2-whiterabbit-GGUF --jinja

Available model files:

  • Huihui-Qwen3.8-27B-abliterated.BF16-mmproj.gguf
  • Huihui-Qwen3.8-27B-abliterated.Q4_K_M.gguf
  • Huihui-Qwen3.8-27B-abliterated.Q5_K_M.gguf
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