Hugging Face's logo

Qwen
/
Qwen3-Coder-30B-A3B-Instruct-FP8

Text Generation
Transformers
Safetensors
qwen3_moe
conversational
fp8
Model card Files
xet
Community
14

Why tokenizer.json is different from the non-FP8 version?

#11
by hibuki - opened
Discussion
hibuki
•
edited Sep 14

It's 11.4MB in Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8
but 7.03MB in Qwen/Qwen3-Coder-30B-A3B-Instruct

Thanks

Sign up or log in to comment