← back to catalog · registered 2026-09-25 03:57

DevQuasar-12/huihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT-GGUF

DevQuasar-12 32B GGUF second-order
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/DevQuasar-12%2Fhuihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT-GGUF"
Response includes
  • classification m8
  • files 14
  • author_summary 4 models
  • readme_text full
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
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
257
Likes
0
Model age
17mo ago
created 2025-04-21

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

Quantizations
Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf text-generation endpoints_compatible region:us conversational

Related

Total size
253 GB
Files
14
Quantizations
7
Registered
2026-09-25 03:57
Last updated on HF
2025-04-21 09:05

Files by quantization

Q8_0 1 file 32.4 GB
huihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT.Q8_0.gguf 32.4 GB 7a36299e download
Q6_K 1 file 25.0 GB
huihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT.Q6_K.gguf 25.0 GB ffe1946b download
Q5_K 2 files 42.7 GB
huihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT.Q5_K_M.gguf 21.7 GB f30c721a download
huihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT.Q5_K_S.gguf 21.1 GB 6a0e6082 download
Q4_K 2 files 36.0 GB
huihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT.Q4_K_M.gguf 18.5 GB a5f5cac0 download
huihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT.Q4_K_S.gguf 17.5 GB 2c91dce8 download
Q3_K 3 files 44.3 GB
huihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT.Q3_K_L.gguf 16.1 GB ca3ebb26 download
huihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT.Q3_K_M.gguf 14.8 GB 0453831e download
huihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT.Q3_K_S.gguf 13.4 GB b5646058 download
Q2_K 1 file 11.5 GB
huihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT.Q2_K.gguf 11.5 GB fa29b04c download
Auxiliary files 4 files 61.0 GB
huihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT.f16-00001-of-00002.gguf 37.1 GB f20496df download
huihui-ai.Qwen2.5-32B-Instruct-abliterated-SFT.f16-00002-of-00002.gguf 23.9 GB e8057bca download
.gitattributes 2.61 KB 3ce27667 download
README.md 895 B cc16cf55 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 - Abliteration, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.