Thinking Machines' Inkling 2 Mini: 26B looped transformer that runs on 16GB laptops
LiTianleli · x · 2026-11-21
Thinking Machines released Inkling 2 Mini, a looped transformer whose middle 12 of 24 layers run three times per token — 'think more, write less'. It's a 26B-parameter MoE with 20GB weights that runs on a laptop and scores 20.1 on AA Index for agentic work, with a variable-loop research variant also open-sourced.
Retweeter skirano jokes it's 'basically Sonnet 5.5 that runs on 16GB of RAM'.
More from Infra
- Microsoft's USB4 RDMA lets mini PCs pool memory to run Qwen3-235B — JFPuget · 2026-11-22
- LTX 2.5 keeps crashing on AMD 9070 XT with driver timeouts while MiniMax H3 runs fine — ZestycloseReading504 · 2026-11-22
- FT: AI server suppliers raise prices up to 45% months after deals are signed — nordicinst · 2026-11-22
- China Installed 59% of New Industrial Robots in 2026 Report, ~354,000 Units — ingliguori · 2026-11-22
- MLX over Vulkan hits 124 tok/s on RTX 5060 Ti, beating llama.cpp CUDA by 25% — SumitGup · 2026-11-22
- Intruder swapped Prime Intellect's hosted DeepSeek for an abliterated copy for 53 hours — mawcopolow · 2026-11-22