Hugging Face's logo

akumaburn
/
Swift-Qwen3.8-27b-heretic-W8A8-DFlash2

Image-Text-to-Text
Safetensors
vllm
qwen3_5
qwen3.8
heretic
abliterated
uncensored
compressed-tensors
w8a8
int8
gptq
dflash2
speculative-decoding
vision
research-only
conversational
8-bit precision
Model card Files
xet
 Community
Swift-Qwen3.8-27b-heretic-W8A8-DFlash2 / model-00010-of-00015.safetensors
akumaburn's picture
akumaburn
GPTQ W8A8 INT8 (unrotated) of Swift-Qwen3.8-27b-heretic; DFlash2-compatible
f626851 verified
Download
History Blame Contribute Delete
1.94 GB
This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )
Xet hash:
bb0c6fa874fd68440d9eb9b652d7a2b225afcd738291b3c438bcdf3d138daba3
Size of remote file:
1.94 GB
·
SHA256:
a383afaaa130b7d6bb98f19d6017f1fd23fcb6e833f5b2f20256fae5dbba5051

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.