Hugging Face's logo

rdtand
/
Qwen3.5-122B-A10B-PrismaQuant-4.75bit-vllm

Image-Text-to-Text
Safetensors
English
multilingual
vllm
qwen3_5_moe
qwen3.5
Mixture of Experts
vision-language
multimodal
deltanet
quantized
mixed-precision
nvfp4
mxfp8
compressed-tensors
prismaquant
mtp
speculative-decoding
conversational
8-bit precision
Model card Files
xet
 Community
Qwen3.5-122B-A10B-PrismaQuant-4.75bit-vllm / model-00004-of-00016.safetensors
rdtand's picture
rdtand
PrismaQuant: GPTQ + closed-form scale_sweep polish (replaces act_round). Measured ~67% per-Linear output-MSE reduction vs prior pipeline in bake-off.
f2011c4 verified
Download
History Blame Contribute Delete
5.09 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:
b151fe398b4e5237eb6becf38c6169136558e552bc2dd8aba48ce3892e06d987
Size of remote file:
5.09 GB
·
SHA256:
f78ecf911ddb6eb5b6b33add207cf52ca8ca2a3e2c88c8437d15e5c8633bf109

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