Open source #Open models Nov 21, 2026 · Originally published Nov 20

Thinking Machines releases Inkling 2 Mini: a looped MoE with about 26B total and 3B active parameters per token, 1M-token context and image input

The local-sized sibling of Inkling 2 Small. How it borrows capacity by looping layers, how it scores against its class, and which runtimes support it on day one.

Image: Hugging Face
Primary source Hugging Face · huggingface.co Read the original ↗

// Key points

  • Of 24 physical decoder layers, the middle 12 loop three times, acting like 48 logical layers; each layer routes to 8 of 128 experts (Small has 384), and a DSpark drafter is included for speed.
  • Against Gemma 4 31B, Qwen3.8-27B, Nemotron 3.5 Super VL and others it leads on 32 of 48 benchmarks; it leads FrontierCode v2.0 and ties Qwen3.8-27B on Terminal-Bench 4.0.
  • Day-one support covers Transformers, llama.cpp (Llama App) and MLX, with SGLang for datacenter deployment; expert weights ship in mixed NVFP4 and MXFP8 precision.
  • A research variant lets you set the loop to 1 or 2 passes for faster inference, though the team says it has not been evaluated in depth.

Builder's take3B active, 1M context and image input sits right in the sweet spot for local or single-GPU serving, and it is the first serious challenger to Qwen3.8-27B. For long-context document understanding in AI Cloud Drive I'd run Inkling 2 Mini against Qwen3.8-27B on the same files, and test the adjustable loop count separately for its speed-quality trade-off.

// Background · from #Open models

Full timeline →
  1. Nov 21 Hugging Face publishes its harness adapter recipe: a LoRA trained with RL inside pi lifts Qwen3.8-27B on hard SWE-bench Pro tasks from 39.2% to 64.7%
  2. Nov 21 Microsoft Foundry Managed Compute is generally available: deploy 150+ open models on dedicated GPUs, choosing NVIDIA A100, H100, H200 or AMD MI300X
  3. Nov 19 Cloudflare opens the weights of Clairic and Clairic-flash: 27B and 9B extraction models that read PDFs and bill only for input tokens

Every Monday, the week in AI in one email

Every Monday morning: the 6 AI stories that mattered most in the past seven days, with my take, in your inbox.

Your email is only used to send the weekly and is never shared. Every email has a one-click unsubscribe link. See the latest issue →