Size / main format35.1072Bsafetensors
Browse AI models
Qwen family AI models
Browse Qwen models and fine-tunes. Check base models, sizes, formats and available downloads.
Browse model families · Choosing a model: formats, memory and licenses
Huihui-Qwen3-VL-8B-Instruct-abliterated
Based on Qwen/Qwen3-VL-8B-Instruct
Model type (creator-reported)abliterateduncensoredfine-tuned
Size / main format8.76712Bsafetensors
Huihui-Qwen3.5-27B-abliterated
Based on Qwen/Qwen3.5-27B
Model type (creator-reported)abliterateduncensoredfine-tuned
Size / main format27.7814Bsafetensors
Huihui-Qwen3.5-9B-abliterated
Based on Qwen/Qwen3.5-9B
Model type (creator-reported)abliterateduncensoredfine-tuned
Size / main format9.6531Bsafetensors
Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP
Base model not specified
Model type (creator-reported)abliterated
Size / main format17.1281Bsafetensors
Huihui-Qwen3.8-27B-abliterated
Based on Qwen/Qwen3.8-27B
Model type (creator-reported)abliterateduncensoredfine-tuned
Size / main format27.7814Bsafetensors
Qwen2.5-VL-7B-Instruct-abliterated
Based on Qwen/Qwen2.5-VL-7B-Instruct
Model type (creator-reported)abliterateduncensoredfine-tuned
Size / main format8.29217Bsafetensors
Size / main format9.6531Bsafetensors
Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP
Source-card excerptSource model card excerpt: ABSOLUTE FIRE: 640 ARC-C for both 8bit and 4bit. Model exceeds 7 of 7 benchmarks for Qwen 3.5 9B, Qwen3.5 27B, Qwen3.6 35B-A3B, and
Model type (creator-reported)abliterateduncensored
Size / main format9.6531BsafetensorsGGUF version available
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP
Source-card excerptSource model card excerpt: Important: This is the first fine tune to exceed 700 "arc-c" (The OpenAI, Claude and Gemini "zone of intelligence") in both 8 bit and
Model type (creator-reported)abliterateduncensoredfine-tuned
Size / main format27.7814BsafetensorsGGUF version available
Qwen3.6-35B-A3B-abliterated-v4
Source-card excerptSource model card excerpt: Qwen3.6-35B-A3B-abliterated-v4 Uncensored version of Qwen/Qwen3.6-35B-A3B with refusal behavior removed via abliteration (norm-preserving orthogonalization). GGUF quantizations: Bahushruth/Qwen3.6-35B-A3B-abliterated-v4-GGUF Blog post: Abliteration: Uncensoring LLMs via Weight Surgery
Model type (creator-reported)abliterateduncensoredfine-tuned
Size / main format34.6606Bsafetensors
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU
Source-card excerptSource model card excerpt: RELEASE 1 GGUFS [including detailed notes, how to use, benches and much more]: - - SOURCE: (THIS REPO) RELEASE 2 GGUFS "Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored": - Stronger,
Model type (creator-reported)uncensoredfine-tuned
Size / main format27.7814Bsafetensors
Qwen3.8-27B-Uncensored-Cyber
Based on philbert440/Qwen3.8-27B-Uncensored-Aggressive
Model type (creator-reported)abliterateduncensoredfine-tuned
Size / main format27.3567BsafetensorsGGUF version available
Qwythos-9B-Claude-Mythos-5-1M
Based on Qwen/Qwen3.5-9B
Model type (creator-reported)uncensoredfine-tuned
Size / main format9.40981Bsafetensors
RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored
Source-card excerptSource model card excerpt: RVN Qwen3.8-Flash-Next Abliterated Uncensored A heavily abliterated derivative built only from the official Qwen3.8-Flash-Next checkpoint, with a measured 2% strict refusal rate ( 2/100
Model type (creator-reported)abliterateduncensoredfine-tuned
Size / main format176.944BsafetensorsGGUF version available
Size / main format180Bsafetensors
No matching models.
Try fewer keywords or remove a filter. This index is a source snapshot, not an exhaustive catalog.