← back to catalog · registered 2026-09-14 14:56

mradermacher/Qwen3.5-9B-Janus-Abliterated-V2-Safetensors-GGUF

mradermacher 9B GGUF
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 2 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.
  • author=mradermacher (M8 quantization producer)
  • is_gguf=1
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 2026-09-14

Variants by this author 2 formats · 0 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Quantizations
F16 Q2_K Q4_K Q6_K Q8_0
Tags
transformers gguf Qwen3.5 janus abliterated merge roleplay uncensored not-for-all-audiences en base_model:SOMEHOTMEAL/Qwen3.5-9B-Janus-Abliterated-V2-Safetensors base_model:quantized:SOMEHOTMEAL/Qwen3.5-9B-Janus-Abliterated-V2-Safetensors

Related

Total size
41.0 GB
Files
7
Quantizations
6
Registered
2026-09-14 14:56
Last updated on HF
2026-09-14 15:26

Files by quantization

F16 1 file 16.7 GB
Qwen3.5-9B-Janus-Abliterated-V2-Safetensors.f16.gguf 16.7 GB 4b07ee1f download
Q8_0 1 file 8.87 GB
Qwen3.5-9B-Janus-Abliterated-V2-Safetensors.Q8_0.gguf 8.87 GB 171b4f9e download
Q6_K 1 file 6.85 GB
Qwen3.5-9B-Janus-Abliterated-V2-Safetensors.Q6_K.gguf 6.85 GB d5cf75bd download
Q4_K 1 file 4.98 GB
Qwen3.5-9B-Janus-Abliterated-V2-Safetensors.Q4_K_S.gguf 4.98 GB 3d08550a download
Q2_K 1 file 3.56 GB
Qwen3.5-9B-Janus-Abliterated-V2-Safetensors.Q2_K.gguf 3.56 GB 53566271 download
Auxiliary files 2 files 2.31 KB
.gitattributes 1.92 KB 368041fd download
README.md 399 B 846c544f download

README current version from Hugging Face

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.