← back to catalog · registered 2026-09-13 15:56

SOMEHOTMEAL/Qwen3-8B-Janus-Abliterated-GGUF

SOMEHOTMEAL 8B GGUF
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
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
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 2026-09-13

Metadata

Quantizations
Q4_K
Tags
gguf endpoints_compatible region:us conversational

Related

Total size
37.4 GB
Files
6
Quantizations
2
Registered
2026-09-13 15:56
Last updated on HF
2026-09-13 15:44

Files by quantization

Q4_K 1 file 4.68 GB
Qwen3-8B-Janus-Abliterated-v1-Q4_K_M-GGUF.gguf 4.68 GB f3a7231c download
Auxiliary files 5 files 32.7 GB
Qwen3-8B-Janus-Abliterated-v1-f16-GGUF.gguf 15.3 GB ec6dee54 download
Qwen3-8B-Janus-Abliterated-v1-Q8_0-GGUF.gguf 8.11 GB 2eb81aba download
Qwen3-8B-Janus-Abliterated-v1-Q6_K-GGUF.gguf 6.26 GB 9c90a46e download
Qwen3-8B-Janus-Abliterated-v1-Q2_K-GGUF.gguf 3.06 GB ff45e6bf download
.gitattributes 1.88 KB e258ca9d download

README

The author did not publish a README.

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.