Forturne
/

Qwen3-Embedding-8B-NVFP4

8-bit precision

compressed-tensors

Model card Files Files and versions

Qwen3-Embedding-8B-NVFP4 / tokenizer.json

Commit History

Upload Qwen3-Embedding-8B NVFP4 (128 cal samples)

afef120
verified

Forturne commited on Mar 3