> ## Content Index
> Fetch the complete content index at: https://claudefox.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# Inkling 2 Mini: Thinking Machines' 26B open model you can run on a laptop
- URL: https://claudefox.com/daily-2026-11-21/
- Published: 2026-11-20T21:10:28.000Z
- Updated: 2026-11-20T21:10:28.000Z
- Description: Thinking Machines released Inkling 2 Mini, an Apache 2.0 looped MoE model of about 20GB that targets 32GB Macs and DGX Spark. Here is which quant fits your memory and what still breaks on launch day.
- Author: hupicake
- Tags: Daily

Thinking Machines released Inkling 2 Mini, an Apache 2.0 looped MoE model of about 20GB that targets 32GB Macs and DGX Spark. Here is which quant fits your memory and what still breaks on launch day.

## [Inkling 2 Mini: how to run Thinking Machines' 26B open model locally, and which quant fits your RAM](https://claudefox.com/inkling-2-mini-run-locally/)

Inkling 2 Mini is Thinking Machines' Apache 2.0 looped MoE model: 26.4B parameters, 3.4B active, about 20GB. Which GGUF quant fits your memory, the commands for llama.cpp, MLX and vLLM, launch-day gaps, and how it compares with Qwen3.8-27B.

[Read the full story](https://claudefox.com/inkling-2-mini-run-locally/)