← November 13, 2026 briefing · added in the 00:00 KST update
Inkling 2 Small follow-up: officially added to Hugging Face Transformers v5.23.0, with 48 MoE layers routing to 8 of 384 experts each
Announced November 13, 2026
Verified (fact)
Hugging Face released Transformers v5.23.0, adding Thinking Machines Lab's 'Inkling 2 Small' to its newly supported models. According to the release notes, the model takes text and images as input and outputs text, and is designed to handle multiple languages beyond English as well as multiple programming languages. The language backbone consists of 48 MoE decoder layers, each routing tokens to 8 of 384 experts. It has 594B total parameters and 17B active parameters. It keeps the original Inkling decoder's learned relative attention, short causal convolutions, and MoE layer setup, and adds block-level attention residuals and gated attention with learned sinks. Whether the weights have been released cannot be confirmed from this material.
Why it matters (interpretation)
Official support in the widely used Transformers library lays the groundwork for companies to build custom applications right away once the previously announced weights are released. The official documentation also discloses architecture details for the first time, making it possible to compare its structure with other large MoE models.
Sources
- Official Release v5.23.0 Hugging Face
Story thread
- 2026-11-06 Thinking Machines Lab releases 'Inkling 2 Small', a 594B-total, 17B-active MoE with image input and long autonomous tasks (community reports)
- 2026-11-07 Inkling 2 Small follow-up: Thinking Machines Lab plans to release weights for enterprise customization (report)
- 2026-11-13 Inkling 2 Small follow-up: officially added to Hugging Face Transformers v5.23.0, with 48 MoE layers routing to 8 of 384 experts each
More about Thinking Machines Lab
-
Inkling 2 Mini follow-up: Ollama v0.40.17 runs it out of the box ('79.2% on SWE-Bench Verified'), adds concurrent requests on Apple silicon
Ollama's v0.40.17 release (tagged rc4) supports Thinking Machines Lab's Inkling 2 Mini. It can be run with a single command, `ollama run...
-
Thinking Machines Lab releases looped open-weight model Inkling 2 Mini: 26B total, 5.4B active, runs on a Mac in ~20GB
Thinking Machines Lab released Inkling 2 Mini, an open-weight model presented on the Hugging Face blog and in the Ollama v0.40.17...
-
Inkling 2 Small follow-up: Thinking Machines Lab plans to release weights for enterprise customization (report)
According to AI Times, Thinking Machines Lab, led by Mira Murati, launched its second-generation model 'Inkling 2 Small' on its official...
-
Thinking Machines Lab releases 'Inkling 2 Small', a 594B-total, 17B-active MoE with image input and long autonomous tasks (community reports)
According to GeekNews, Thinking Machines Lab has released 'Inkling 2 Small', its second-generation MoE model. It has 594 billion total...