Intel
/

Qwen3-Next-80B-A3B-Thinking-int4-AutoRound

Text Generation

4-bit precision

Model card Files Files and versions

Resources

View closed (0)

What Token Generation are you guys getting with CPU only?

#3 opened 26 days ago by

Qwen/Qwen3-Next-80B-A3B-Thinking has MMLU_PRO 82.7 but you guys get 0.7271

#2 opened 3 months ago by

Difference between int4-mixed and int4

#1 opened 3 months ago by