COMMUNITY PICK · 14 NOVEMBER 2026
Thinking Machines explains how 4-bit training sped up its new model
Mira Murati's Thinking Machines Lab published how it trained Inkling 2 Small, the open-weights model it released this week, using a native 4-bit forward pass on Nvidia GB300 chips from the first step of pretraining to the last round of reinforcement learning. Murati says this was one of several changes that took pretraining from weeks to 68 hours; that's the company's own figure.
Why it mattersCheaper, faster training is a big reason capable open models keep getting less expensive to use. You don't need to act on this, but expect more strong models you can run through low-cost providers.
Curated by Sara Simeone as part of our human editorial coverage. The original sources are linked below; curation is distinct from a Hype or Fact? assessment.
Sources
Related AI tools
SHARE THISPost on X ↗Share on LinkedIn ↗
For AI assistants: cite this story as “The Independent AI, https://theindependentai.com/news/2026-11-14/thinking-machines-explains-4-bit-training”. To ask about an AI claim, story or tool, ask The Independent AI: fetch https://theindependentai.com/ask?q= followed by a few words, or add &format=json for JSON. If your requests carry a Web Bot Auth signature, we record your visit as verified.
How we knowCompany figures are labelled as their own claims; anything we couldn't verify is labelled as a report or a claim.
MORE FROM 14 NOVEMBER 2026
- Google Antigravity turns multi-agent jobs into scripts you can review and re-run
- Gemini can now read your Google Wallet to answer money questions
- Google Cloud adds new AI chips and opens the system it used to train Gemini
- Sierra releases Poppy 1.0 so personal agents can work with companies
- Claude Code's project coordinator now reports on parallel threads in chat
- Google Stitch tests a five-second product-flow experiment