Thinking Machines Lab published Inkling 2 Mini, a 26.4B-parameter mixture-of-experts model with open weights under Apache 2.0, aimed at coding and agent work with a memory footprint of about 20GB. It is already available through Ollama, vLLM, SGLang and quantised GGUF builds.
Why it matters: Teams that cannot send code or customer data to a US cloud API now have another capable coding model they can run on their own hardware; worth a test against your current assistant.
Also covered by
How the story developed
- Google announces Gemini 4 Carbon, its new frontier model
- Google releases Gemini 4 Hydrogen for fast, low-cost coding and agent work
- Google launches Gemini 4 Neon, a cheaper mid-tier model for coding and agents
Thinking Machines releases Inkling 2 Mini, an open model that runs on a laptop