PulseAugur
EN
LIVE 12:18:39

Thinking Machines releases Inkling 2 Small multimodal MoE model

Thinking Machines has released Inkling 2 Small, a multimodal MoE model with 594B total parameters and 17B active parameters. The model boasts a 1M context window and was pretrained in under 3 days on 12T tokens using NVFP4 precision. It is positioned as a leading open-weight model, with Apache 2.0 weights expected after safety testing. AI

IMPACT Sets a new benchmark for open-weight models, potentially accelerating research and development in multimodal AI.

RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on Latent Space (swyx) →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Thinking Machines releases Inkling 2 Small multimodal MoE model

How we ranked this

Signal score
54 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Latent Space (swyx) TIER_1 English(EN) · swyx .ai ·

    [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.