RedHatAI
/

Qwen3.5-122B-A10B-NVFP4

compressed-tensors

8-bit precision

Model card Files Files and versions

Resources

View closed (0)

Any plans on NVFP4 quantization of smaller Qwen3.5 models (like 35B-A3B and 27B)?

#2 opened 28 days ago by

Use Qwen2TokenizerFast tokenizer class for vllm support

#1 opened about 1 month ago by