Thinking Machines Lab releases Inkling 2 Small model weightsMachine translation

@rohanpaul_ai You slipped “594B” and “Small” into the same sentence so casually 😂

Thinking Machines Lab kept its promise and open-sourced Inkling 2 Small, a 594B-parameter model trained with 4-bit forward passes. > now available for download on HuggingFace under an Apache 2.0 licens > Training in 4-bit cut pretraining time 8% and RL time 20%, for about 2% efficiency loss. > Running it takes at least 500GB of GPU memory in NVFP4 and at least 800GB in MXFP8, and MXFP8 gains “a very marginal 1–2 percentage points” over NVFP4 on evals. > Because training kept the same numerics from pretraining through the final RL rollout, the released 4-bit checkpoint needed no separate calibration step. > The lab first tried NVFP4 in both forward and backward passes, but that hurt compute efficiency too much, so only the forward pass stays in 4-bit.