#Inkling2Mini
Launched this week on TrustList: Inkling 2 Mini

Thinking Machines Lab's open-weights Inkling 2 Mini of 20 November 2026: Apache 2.0, 26.4 billion parameters with 3.4 billion active, text and image input, a context of up to one…

#Inkling2Mini #NewProduct #startups
trustlist.uk/launches/launch-th…
TrustList: Software & IT Services Rankings, Insights and Reviews
Independent rankings of software and IT services by category and country, daily tech and business insights, and reviews from real users. Free for buyers.
trustlist.uk
November 21, 2026 at 5:20 PM
Thinking Machines just dropped Inkling 2 Mini – a 26B looped MoE that nailed 27/28 benchmarks. Curious how a mini model outperforms the giants? Dive into the results! #Inkling2Mini #LoopedMoE #LLMBenchmarks

🔗 aidailypost.com/news/thinkin...
November 21, 2026 at 12:27 PM
Thinking Machines ra mắt Inkling 2 Mini: model mở 26,4 tỷ tham số chạy được trên MacBook, dẫn đầu coding trong nhóm model nhỏ

https://news.danhthanh.dev/bai/thinking-machines-ra-mat-inkling-2-mini-model-mo-26-4-ty-7t030b

#AIModel #QuocTe #HOT #Inkling2Mini #ThinkingMachines #OpenWeights
Thinking Machines ra mắt Inkling 2 Mini: model mở 26,4 tỷ tham số chạy
Thinking Machines Lab vừa phát hành Inkling 2 Mini — một model mở trọng số chỉ 26,4 tỷ tham số nhưng
news.danhthanh.dev
November 21, 2026 at 10:04 AM
Discover the latest features of the Inkling 2 Mini! This powerful tool is designed to enhance your creative projects with precision and versatility. Dive into its innovative capabilities and see how it can elevate your workflow! #Inkling2Mini #Innov…

https://thinkingmachines.ai/news/inkling-2-mini/
November 21, 2026 at 1:02 AM
The Inkling 2 Mini model from Thinking Machines contains 26 billion parameters with 5.4 billion active and fits on a Mac (about 20 GB). It handles text, images, tool calls, and thinking, and scores 79.2% on SWE-Bench Verified.

#Ollama #Inkling2Mini #ThinkingMachines
Inkling 2 Mini runs on 20GB of Mac memory
Source: ollama
realfeedapp.com
November 21, 2026 at 12:40 PM
Thinking Machines Releases Inkling 2 Mini for Local AI Use

https://newisty.com/blog/thinking-machines-releases-inkling-2-mini-for-local-ai-use?utm_source=social&utm_campaign=crypto_news

#ai #thinkingmachines #inkling2mini
November 21, 2026 at 8:25 AM
Inkling 2 Mini thought for 15 minutes before writing a single line of code.

Then it passed all 32 checks and all 12 traps in the spec.

I tested Thinking Machines' new open model on a 16GB GPU: agent tasks, vision and speed.

youtu.be/SAc7Eq64L1I

#LocalLLM #Inkling2Mini
Inkling 2 Mini on a 16GB GPU: 5/5 Agent Tasks, 20/22 Vision
YouTube video by Zero to MVP
youtu.be
November 21, 2026 at 7:19 PM
「Thinking Machines Labが新型ローカルAI『Inkling 2 Mini』をオープンウェイト公開!手元のPCで動く小型サイズながらコーディング首位を獲得」

中間12層を3回ループさせる独自構造により、26.4B(稼働3.4B・容量約20GB)の省メモリと深い推論力を両立。100B未満の公開モデルでコード修正・検索ベンチマーク首位を記録し、画像入力や100万トークンにも対応)。

thinkingmachines.ai/news/inkling...
#ThinkingMachines #Inkling2Mini #ローカルLLM #生成AI #AI開発 #オープンソース
Introducing Inkling 2 Mini
Inkling 2 Mini is an open-weights model small enough to run on your laptop. It loops its middle layers to reason more per token and reach answers in fewer tokens.
thinkingmachines.ai
November 22, 2026 at 2:40 AM