From the source
Thinking Machines Lab has released Inkling 2 Mini, an open-weights model small enough to run on a laptop, after users said the 594B-parameter Inkling 2 Small was too big.
- The weights are on
Hugging Face, and the model is live on Tinker for inference and fine-tuning, with chat in the Tinker Playground.
- Inkling 2 Mini is a looped transformer: of its 24 layers, the middle 12 run three times per token while the first and last six run once.
- It is a Mixture-of-Experts model with 26.4B total parameters, 3.4B active and 5.4B weight activations per token once looping is counted.
- Most weights were trained and deployed natively in NVFP4, with the last four layers in MXFP8, so the full footprint sits around 20GB with no quantization loss.
- According to Thinking Machines, it leads every open-weights model under 100B total parameters on DeepSWE v1.1 with 48.2% and Vals Index v2.2 with 46.5%, and ties Qwen3.8-27B at 20.1 on the Artificial Analysis Index.
- The company says it trails Qwen3.8-27B on multi-turn chat and on instructions with many constraints, and that it is ~6x cheaper and ~4x faster per task.