Qwen
/

Qwen3.5-397B-A17B-FP8

Image-Text-to-Text

Model card Files Files and versions

Resources

View closed (0)

When can we expect 4B, 8B, and 10B versions?

#8 opened 1 day ago by

Is there possible to see 32B dense version?

#7 opened 1 day ago by

Memory Requirements to run `Qwen/Qwen3.5-397B-A17B-FP8`

#6 opened 1 day ago by

Gibberish output with vllm nightly qwen3_5 build

#5 opened 2 days ago by

mxfp4 QAT versions?

#4 opened 2 days ago by

can we deploy this using tp (H100-80GB each)=6 ?

#3 opened 2 days ago by

ValueError: Weight output_partition_size = 16 is not divisible by weight quantization block_n = 128

#2 opened 2 days ago by

Qwhen are you making an 8b version???

#1 opened 2 days ago by