# Inkling 2 Mini

> The smallest second-generation Inkling — a 26.4B / 3.4B-active looped MoE with Apache-2.0 weights, sized for local machines.

- Maker: Thinking Machines Lab
- Line: Inkling
- Canonical page: https://ai-tldr.dev/models/inkling-2-mini/
- Updated: 2026-11-20

## In short

Inkling 2 Mini is the smallest model in Thinking Machines Lab's second Inkling generation, released on November 20, 2026. It is a Mixture-of-Experts looped transformer with 26.4 billion total and 3.4 billion active parameters. It has a 1M-token context window. You can use it through Tinker (Thinking Machines) and Hugging Face (open weights).

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 1M | [1] |
| Licence | Apache-2.0 · open weights | [1] |
| Released | 20 November 2026 | [2] |
| Parameters | 26.4B total · 3.4B active | [1] |

## Sources

1. [Inkling 2 Mini model card](https://thinkingmachines.ai/model-card/inkling-2-mini/)
2. [Inkling 2 Mini announcement](https://thinkingmachines.ai/news/inkling-2-mini/)

## Overview

Inkling 2 Mini is the smallest model in Thinking Machines Lab's second Inkling generation, released on November 20, 2026. It is a Mixture-of-Experts looped transformer with 26.4 billion total and 3.4 billion active parameters. The Hugging Face model card lists text and image input, text output, a context window of up to 1M tokens and the Apache 2.0 license.

The model stores 24 layers in four blocks of six. The two middle blocks run three times per token, so the model applies 48 layers from 24 stored ones; counting the loops, the lab gives 5.4B weight activations per token. Thinking Machines reports that looping the middle layers gave larger gains than looping the last layers on 27 of 28 evaluations.

Training began with 384 experts per layer. Two-thirds were pruned during midtraining, leaving 128, and the model was healed with distillation on 1T tokens. Most weights are NVFP4 and the last four layers are MXFP8, the precisions the model was trained in, and the lab gives a memory footprint of about 20GB.

## Strengths

- About 20GB of memory; the lab lists Ollama on Macs with at least 32GB of RAM
- Reported 79.2% on SWE-bench Verified, against 77.8% for Qwen3.8-27B
- Reported 82.7% on MCP Atlas and 79.0% on BrowseComp with compaction
- Up to 1M tokens of context with text and image input

## Best for

- Reach for it to run a coding or agent model locally on a 32GB Mac or an NVIDIA DGX Spark.
- Reach for it to fine-tune a small open model on Tinker or with SkyRL, Miles or NVIDIA AutoModel.
- Reach for it to study looped transformers, alongside the TML-d24-varloop-research model released with it.

## How to access

- [Tinker (Thinking Machines)](https://tinker-docs.thinkingmachines.ai/tinker/)
- [Hugging Face (open weights)](https://huggingface.co/thinkingmachines/Inkling-2-Mini)

## Inkling versions

- Inkling 2 Mini (20 November 2026): Smallest second-generation model — 26.4B / 3.4B-active looped MoE, about 20GB, Apache-2.0 weights. — this page
- [Inkling 2 Small](https://ai-tldr.dev/models/inkling-2-small/) (5 November 2026): Second generation — 594B / 17B-active MoE, text and image input; Apache-2.0 weights since November 12, 2026.
- [Inkling-Small](https://ai-tldr.dev/models/inkling-small/) (30 July 2026): Efficient 276B / 12B-active sibling of Inkling, Apache-2.0.
- [Inkling](https://ai-tldr.dev/models/inkling/) (15 July 2026): First release — 975B / 41B-active MoE, Apache-2.0.

## FAQ

### What is Inkling 2 Mini?

Inkling 2 Mini is Thinking Machines Lab's smallest second-generation model, released on November 20, 2026. It is a 26.4B total / 3.4B active looped Mixture-of-Experts model with text and image input, up to 1M tokens of context and Apache-2.0 weights on Hugging Face.

### What does looping mean in Inkling 2 Mini?

Inkling 2 Mini runs its two middle blocks of six layers three times for every token, so 24 stored layers act as 48. Thinking Machines Lab says the middle layers carry more abstract reasoning, and looping them beat looping the last layers on 27 of 28 evaluations.

### How much memory does Inkling 2 Mini need?

Thinking Machines Lab gives Inkling 2 Mini a memory footprint of about 20GB, with most weights in NVFP4. The lab lists Ollama support on Macs with at least 32GB of RAM, GGUF builds through Unsloth and llama.cpp, and NVIDIA DGX Spark.

## Links

- [Inkling 2 Mini announcement](https://thinkingmachines.ai/news/inkling-2-mini/)
- [Inkling 2 Mini model card](https://thinkingmachines.ai/model-card/inkling-2-mini/)
- [Inkling 2 Mini on Hugging Face](https://huggingface.co/thinkingmachines/Inkling-2-Mini)
- [Tinker documentation](https://tinker-docs.thinkingmachines.ai/tinker/)
- [Thinking Machines Lab](https://thinkingmachines.ai/)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/inkling-2-mini/
