Thinking Machines released Inkling 2 Mini, a 26B total / 5.4B active parameter mixture-of-experts model built on a looped transformer architecture, open-sourced under Apache 2.0 with text and image input and a 1M token context window. It scores 20 on the Artificial Analysis Intelligence Index, matching Qwen3.8 27B and Nanbeige4.3-33B with roughly 5x and 6x fewer active parameters respectively, sits on the Pareto frontier for intelligence versus size, and is small enough to run on a MacBook or DGX Spark.
Inkling 2 Mini
Multimodal MoE model with 26B total and 3.5B active parameters, featuring looped layers and a native DSpark speculator.
Curated Intelligence
Thinking Machines has released Inkling 2 Mini, a 26B-parameter looped transformer small enough to run on a laptop yet capable of agentic work, scoring 20.1 on the AA Index. The model is now live across Arena.ai's Agent Arena, Code Arena and Text Arena, with leaderboard results pending.
Thinking Machines has released Inkling 2 Mini, a 26B-total, 5.4B-active-parameter looped-transformer mixture-of-experts model scoring 20 on the Artificial Analysis Intelligence Index, placing it on the Pareto frontier for intelligence versus active parameters. Released under Apache 2.0 with text and image input and a 1M-token context window, it is small enough to run locally on a MacBook or DGX Spark.
Inkling released Inkling 2 Mini, an open-weights model built on a looped transformer that runs its middle layers three times per token to reason with fewer tokens. The MoE model has 26.4B total and 3.4B active parameters, scoring 48.2% on DeepSWE v1.1 and 46.5% on Vals Index v2.2, which it claims leads all open-weights models under 100B while running locally on a laptop.
Thinking Machines Lab and Hugging Face released Inkling 2 Mini, a multimodal Mixture-of-Experts model for local deployment with roughly 26B physical and 3B active parameters per token. Its key trick is looping certain layers three times to boost effective capacity, alongside a 1M-token context, image and text input, and mixed-precision NVFP4/MXFP8 expert weights with a DSpark drafter for extra speed.
Thinking Machines released Inkling 2 Mini, a multimodal MoE with 26B total and 3.5B active parameters, up to 1M token context, and a native DSpark speculator. Its key innovation is a looped architecture where the middle 12 layers run three passes with shared weights, each keeping its own KV cache and reading gated messages from the prior pass. vLLM shipped day-0 support on NVIDIA Blackwell, Hopper, and DGX Spark.