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
76.7 GB
  • 1 contributor
 History: 8 commits
rdtand's picture
rdtand
PrismaQuant final: visual NVFP4 (108/110 DP-placed), lm_head BF16 (vLLM ParallelLMHead runtime limit), pos_embed excluded
2f54276 verified