ResearchNovember 16, 2026
-24
🧊
4-Bit Training: Inkling 2 Small Defies Precision Loss
Thinking Machines analyzes 4-bit training and compares BF16, MXFP8 and NVFP4.
#Quantization#Training#NVFP4#LLM#Thinking Machines

🔥 What happened
A team trained Inkling 2 Small, the largest known model with an end-to-end native 4-bit forward pass. It uses NVFP4 for expert layers and MXFP8 for backward passes on Nvidia GB300.
💡 Why it matters
NVFP4 stores 3.6x fewer bits than BF16 and runs up to 6x faster. The payoff: 8% faster pretraining wall-clock and 20% faster RL—without wrecking accuracy.
⚡ Our take
Training in FP16 now looks like burning compute for sport. But beware: this 4-bit recipe needs specific hardware and custom kernels—not plug-and-play.
The title, summary and analysis of this item were produced automatically by an AI system and have not been editorially reviewed. They may contain errors, bias or omissions — when in doubt, read the linked original source.
Deep Dives & Similar Intelligence

165M Model Trained for $4,200
ResearchNovember 15, 2026
Alibaba open-sources its code review agent
Tools & ProjectsNovember 13, 2026

Microsoft VP ships GPU task manager
Tools & ProjectsNovember 12, 2026

145B Model Runs on a Laptop
AI modelsNovember 12, 2026

Tencent's Hy4 Flash Slashes AI Costs
AI modelsNovember 16, 2026