Llama-3.3-70B-Instruct-abliterated
70BLlama
from meta-llama/Llama-3.3-70B-Instruct
↓ 122.9K♥ 9422 repos
50B – 100B abliterated models
50B – 100B abliterated models are refusal-ablated open-weight models whose parameter count falls in the 50B – 100B range — typically a multi-GPU deployment. 13 are indexed here, ordered by total downloads.
13 models↓ 311.8K downloads
Qwen2.5-72B-Instruct-abliterated
72BQwen
from Qwen/Qwen2.5-72B-Instruct
↓ 54.5K♥ 8816 repos
Qwen3-Next-80B-A3B-Instruct-abliterated
80BQwen
↓ 26.8K♥ 69 repos
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-Uncensored
74BNemotronuncensored
from nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16
↓ 19.3K♥ 16
Meta-Llama-3-70B-Instruct-abliterated-v3.5
70BLlama
from failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5
↓ 19K♥ 5615 repos
llama-3-70B-Instruct-abliterated
70BLlama
from failspy/llama-3-70B-Instruct-abliterated
↓ 13K♥ 15416 repos
Smaug-Llama-3-70B-Instruct-abliterated-v3
70BLlama
from failspy/Smaug-Llama-3-70B-Instruct-abliterated-v3
↓ 11K♥ 164 repos
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-Abliterated
74BNemotron
from nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16
↓ 9.5K♥ 12
ai_DeepSeek-R1-Distill-Llama-70B-abliterated
70BLlama
from huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated
↓ 8.9K♥ 463 repos
Hermes-4-70B-heretic
70BOtherheretic
from meta-llama/Llama-3.1-70B
↓ 7.2K♥ 33 repos
Qwen3-Next-80B-A3B-Thinking-abliterated
80BQwen
↓ 7.2K♥ 67 repos
Llama-3.3-70B-Instruct-ablated
70BLlamauncensored
from NaniDAO/Llama-3.3-70B-Instruct-ablated
↓ 6.7K♥ 217 repos
Hermes-3-Llama-3.1-70B-Uncensored
70BLlamauncensored
from NousResearch/Hermes-3-Llama-3.1-70B
↓ 5.7K♥ 164 repos