Termsslug: mxfp8

MXFP8

8-bit microscaling float format with higher memory footprint but marginally better evals than NVFP4.

Curated Intelligence

1 items · Page 1/1
Rohan Paul (@rohanpaul_ai)T2·Models
78 pts
Thinking Machines Open-Sources 594B-Parameter 4-Bit Trained Model

Thinking Machines Lab has fulfilled its promise by open-sourcing Inkling 2 Small under Apache 2.0, a 594B-parameter model trained with native 4-bit forward passes from the first pretraining step through the final RL rollout. The 4-bit approach cut pretraining time by 8% and RL time by 20% for roughly 2% efficiency loss, and the released checkpoint requires no separate calibration.