# TestingCatalog — Thinking Machines releases Inkling 2 Mini open-weight model

- Company: TestingCatalog (testingcatalog.com)
- Announced: 2026-11-20T22:07:14+00:00
- Category: open-weight-release
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://www.testingcatalog.com/thinking-machines-releases-inkling-2-mini-looped-open-model/
- Record: https://forck.live/items/39445-thinking-machines-releases-inkling-2-mini-open-weight-model
- Subject: AI models / agents / unreleased features
- Open weights: yes
- Models affected: Inkling 2 Mini, Inkling 2 Small, Qwen3.8-27B, GPT-6 Luna
- License: Apache 2.0
- Context window: 1M token context window
- Pricing: $0.59 and takes 9.0 minutes per Intelligence Index task vs. $3.53 and 38.2 minutes for Qwen3.8 27B

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.

## Evidence

Verbatim from https://www.testingcatalog.com/thinking-machines-releases-inkling-2-mini-looped-open-model/:

> Thinking Machines Lab has released Inkling 2 Mini, an open-weights model built to be fast, capable at agentic work, and small enough to run on a laptop. The weights for Inkling 2 Mini and a research-specific variable-loop variant are on Hugging Face, and the model is live on Tinker for inference and fine-tuning, with chat in the Tinker Playground.
> 
> Open-source inference is supported from day one on SGLang, vLLM, Ollama, Unsloth, NVIDIA Dynamo and TokenSpeed, with RL fine-tuning on SkyRL, Miles and NVIDIA AutoModel.
> 
> Some of you thought that Inkling 2 Small was too big at 594B parameters. We heard you: Inkling 2 Mini is a looped transformer with just 26B parameters, small enough to run on your laptop, powerful enough for agentic work with a score of 20.1 on AA Index. https://t.co/9HzaUMwghb
> 
> 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, letting the model apply more reasoning and reach the right answer with fewer tokens. 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.

---

Record: https://forck.live/items/39445-thinking-machines-releases-inkling-2-mini-open-weight-model
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
