PulseAugur
EN
LIVE 21:39:36

Thinking Machines releases Inkling, a 1T-parameter multimodal LLM with 1M context

Thinking Machines has released Inkling, a large multimodal language model with approximately 1 trillion parameters and a 1 million token context window, available on Hugging Face. This model natively processes text, images, and audio, and is designed for domain adaptation through fine-tuning. Inkling features a Mixture-of-Experts architecture with 41 billion active parameters, utilizing relative attention, hybrid attention (global and sliding window), and short convolutions for efficient inference. AI

IMPACT Enables new multimodal reasoning applications with its 1T parameters and 1M context window.

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

Read on Hugging Face Blog →

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

Thinking Machines releases Inkling, a 1T-parameter multimodal LLM with 1M context

COVERAGE [1]

  1. Hugging Face Blog TIER_1 English(EN) ·

    Welcome Inkling by Thinking Machines