Thinking Machines has released Inkling-Small, a 276 billion parameter Mixture-of-Experts model designed to run on a single GPU. This development allows for more accessible deployment of large-scale AI models. The announcement was part of a broader AI briefing that also touched on NVIDIA's work in agentic reinforcement learning and other industry developments. AI
IMPACT Enables wider deployment of large AI models by reducing hardware requirements.
RANK_REASON This is a model release from a company that is not a Tier-1 frontier lab, and the focus is on its accessibility (running on one GPU) rather than a breakthrough performance claim.
Read on Mastodon — fosstodon.org →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
