The Tech Gazette · Inkling 2 https://techgazette.com.br/story/inkling-2/ Every piece of the story "Inkling 2", from its sources' own pages — primary sources only. en 180 Thu, 12 Nov 2026 19:31:00 GMT Inkling 2 Small Now Available in Snowflake Cortex Training https://www.snowflake.com/content/snowflake-site/global/en/blog/inkling-2-small-snowflake-cortex-training https://www.snowflake.com/content/snowflake-site/global/en/blog/inkling-2-small-snowflake-cortex-training Thu, 12 Nov 2026 19:31:00 GMT Snowflake News · News Snowflake — Inkling 2 Small, Thinking Machines Lab's open-weight agentic model, is now in Snowflake Cortex Training for batch and streaming inference on governed data. Inkling 2 Small now available on AI Gateway https://vercel.com/changelog/inkling-2-small-now-available-on-ai-gateway https://vercel.com/changelog/inkling-2-small-now-available-on-ai-gateway Thu, 12 Nov 2026 00:00:00 GMT Vercel Availability · News Vercel — Inkling 2 Small from Thinking Machines is now available on AI Gateway. The multimodal reasoning model supports coding agents, visual understanding, and professional knowledge work, with text and image inputs and text out… Inkling 2 Small on vLLM: Day-0 Support https://vllm.ai/blog/2026-11-12-inkling2-small https://vllm.ai/blog/2026-11-12-inkling2-small Thu, 12 Nov 2026 00:00:00 GMT vLLM News · News vLLM — vLLM supports Thinking Machines' Inkling 2 Small from day 0: attention residuals, a new decode kernel for relative-bias attention, all-reduce fused with the ops around it, and DSpark speculative decoding. New model: Thinking Machines: Inkling 2 Small https://openrouter.ai/thinkingmachines/inkling-2-small https://openrouter.ai/thinkingmachines/inkling-2-small Mon, 09 Nov 2026 22:04:00 GMT OpenRouter Release · New Models OpenRouter — Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second... [AINews] Inkling 2 Small: 17A-594B trained in 68 hours on 12T tokens, beating Muse Spark https://latent.space/p/ainews-inkling-2-small-17a-594b-trained-in-68-hours-on-12t-tokens-beating-muse-spark/ https://latent.space/p/ainews-inkling-2-small-17a-594b-trained-in-68-hours-on-12t-tokens-beating-muse-spark/ Fri, 06 Nov 2026 10:35:00 GMT swyx (Latent Space) Analysis · Columns swyx (Latent Space) — November 5, 2026 — Inside Inkling 2 Small’s training run and METR’s study of AI research at Anthropic.