Hugging Face's logo

CCSSNE
/
tarruda-Qwen3.5-397B-A17B-heretic-smol-IQ2_XS-GGUF

Text Generation
GGUF
imatrix
heretic
abliterated
uncensored
conversational
qwen3_5_moe
Model card Files
xet
 Community

This is just Qwen 3.5 397B heretic quantized down to 2.46 BPW using ubergarm smol-IQ2_XS recipe (https://huggingface.co/ubergarm/Qwen3.5-397B-A17B-GGUF).

Downloads last month
91
GGUF
Model size
396B params
Architecture
qwen35moe
Hardware compatibility
Log In to add your hardware

2-bit

Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for CCSSNE/tarruda-Qwen3.5-397B-A17B-heretic-smol-IQ2_XS-GGUF

Base model

RadicalNotionAI/Qwen3.5-397B-A17B-heretic
Quantized
Sabomako/Qwen3.5-397B-A17B-heretic-bf16-GGUF
Quantized
(4)
this model

Collection including CCSSNE/tarruda-Qwen3.5-397B-A17B-heretic-smol-IQ2_XS-GGUF