analiza aiqbench
Thinking Machines has released Inkling 2 Small, a 17B active parameter multimodal MoE model trained on 12T tokens in just 68 hours. The system demonstrates competitive performance against Western open-weight counterparts while emphasizing intentional customizability for agentic workflows and context graph integration. Weights are expected to be open-sourced under Apache 2.0 following external safety testing next week.
[AINews] Inkling 2 Small: 17A-594B trained in 68 hours on 12T tokens, beating Muse Spark
November 5, 2026 — Inside Inkling 2 Small’s training run and METR’s study of AI research at Anthropic.
Build AI systems with context graphs and agentic memory. Join Andrew Ng and AI engineers at NODES 2026 for 100+ live technical sessions. Free, online, 24 hours. Save your spot! People are of course comparing with Western models like Mistral, Reflection and Meta Muse. People are calling it “the smartest western open weight model by a margin”, and while it is certainly competitive in that league, what’s probably the most interesting is the intentional “customizability” of Inkling, which leans into the overall Thinky and Tinker messaging: AI News for 11/04/2026-11/05/2026 is brought to you by our friends at Neo4J, who’s talks are doing gangbusters! Build AI systems with context graphs and agentic memory. Join Andrew Ng and AI engineers at NODES 2026 for 100+ live technical sessions. Free, online, 24 hours. Save your spot! Thinking Machines released Inkling 2 Small, a 594B-total / 17B-active multimodal MoE. It is available now on Tinker, and Apache 2.0 weights are promised "next week" after external safety testing. Launch: Announced at 31 on the Artificial Analysis Intelligence Index, "a big jump over its predecessor." Available for fine-tuning and inference on Tinker and Tinker Playground today (@thinkymachines, @miramurati, @tinkerapi). Launch: Announced at 31 on the…
Extras afișat conform termenilor RSS ai publicației · 200 cuvinte · textul integral și figurile sunt pe site-ul publicației