Thinking Machines — AI news & models

Models 🇺🇸

Thinking Machines Unveils Open Multimodal Model Inkling with Trillion Parameters

Thinking Machines has released on Hugging Face the open multimodal model Inkling, which understands text, images, audio, and video, supports a context of up to 1 million tokens, and has approximately 975 billion parameters. The model is available in BF16 and NVFP4 versions, works with popular frameworks (Transformers, SGLang, vLLM), and includes fast inference mechanisms.

Hugging Face blog27.07 · 03:03

Models 🇺🇸

Poolside Releases Laguna S 2.1 — an Open-Weight Model for Agentic Coding That Punches Above Its Weight Class in SWE-Bench Multilingual

Poolside released Laguna S 2.1, an open-weight model with 11.8 billion parameters and 8 billion active per token, designed for agentic coding. Based on a Mixture-of-Experts (MoE) architecture, it supports up to 1 million tokens of context and can run on a single NVIDIA DGX Spark. Laguna S 2.1 ranks first among open models with known size on Terminal-Bench 2.1 (70.2%) and SWE-Bench Multilingual (78.5%), outperforming many larger competitors.

Poolside

DeepSeek

NVIDIA

Tencent

Moonshot AI

Alibaba/Qwen

Anthropic

MarkTechPost24.07 · 05:04