Inkling 2 Small trained partly in NVFP4 with mixed-precision recipe
HanGuo97 · x · 2026-11-14
Jack Cook's team released Inkling 2 Small, their first model trained partly in NVFP4. A mixed-precision recipe delivers a strong tradeoff between speed and accuracy; the accompanying post details how it was done and lessons learned along the way.
More from Research
- SFT-ing small models for weight-space programming hits 99.8% on logit lens — lateinteraction · 2026-11-14
- Third-person self-talk regulates emotion without cognitive control, fMRI study shows — AnnaCiaunica · 2026-11-14
- PiHand: latent hand-object interaction priors cut dexterous-hand RL training data 10x — KyleMorgenstein · 2026-11-14
- New paper: symmetry as a common origin of hierarchical emergence and abstraction — mjdramstead · 2026-11-14
- MoE combine traffic cut from 16 to 8.25 bits per value via RHT + S2F6 quantization — snowclipsed · 2026-11-14
- Scientists simulate an entire living cell in 4D, published in Cell — tomchapin · 2026-11-14