abliteratedmodels.org

GGUF abliterated models

GGUF abliterated models are refusal-ablated models published in GGUF format — the llama.cpp container format, which runs on CPU or mixed CPU/GPU and is the usual choice for local evaluation. 554 models in this index ship at least one GGUF repository.

554 models45.3M downloads

Qwythos-9B-v2

9BOtheruncensored

from empero-ai/Qwythos-9B-v2

639.9K26611 repos

Qwythos-27B-v1

27BOtheruncensored

from empero-ai/Qwythos-27B-v1

342.3K1667 repos

qwen3.6-27b

27BQwenuncensored

from Qwen/Qwen3.6-27B

89K83 repos

Homura-30B

30BOtherheretic

from darkc0de/Muse-Glimmer-30B-heretic

68.8K313 repos

Dolphin3-Cyber-8B

8BOtheruncensored

from huihui-ai/Dolphin3.0-Llama3.1-8B-abliterated

50.6K1764 repos

Showing the 120 most-downloaded of 554 models in this group. The remaining 434 are reachable through the full paginated index and are all listed in the sitemap.