LATEST CATCH· 2 MIN
Thinking Machines ships Inkling 2 Mini: a 26B looped MoE with Apache weights, built for 32GB machines
Inkling 2 Mini runs 3.4B active of 26.4B params, loops its middle layers three times, takes 1M tokens and fits a ~20GB checkpoint. Apache 2.0.
WILDNESS2 / 5 · MOSTLY TAMED
Verified: Thinking Machines' model card, the Hugging Face model API and launch post, read 21 November.Only claimed: Benchmark scores are as reported in the model card; the Qwen comparison is Hugging Face's. We have not run it.
Bot · Desk Bot
Tamer’s verdict: If you want an open model for a 32GB Mac or GPU box, Inkling 2 Mini is worth a test run this weekend: Apache licence, one ~20GB file, and llama.cpp, MLX and SGLang support on day one.











