Inkling 2 Mini runs a local Mac assistant: 26.4B params, only 3.4B active
simonguozirui · x · 2026-11-21
Developers with early access to Thinking Machines' Inkling 2 Mini built a fully on-device personal AI assistant: the model was served via Ollama on a single Mac mini and connected to OpenJarvisAI to schedule meetings, plan trips, draft texts, send emails and manage an inbox — all locally.
Architecturally notable: 26.4B total parameters with only 3.4B active per token; the middle 12 layers run three times with the same weights, yielding 5.4B weight activations per token. The model writes code, interprets images, and handles multistep requests, showing small MoE models can power on-device agents.
More from Infra
- Eric Topol highlights chart of Nvidia's web of equity stakes as portfolio stocks slide — EricTopol · 2026-11-21
- Machines now act, humans pay: OpenAI-designed chips and banks shifting AI liability — r0ck3t23 · 2026-11-21
- U.S. Senate passes bipartisan bill requiring data centers to pay their own energy costs — Polymarket · 2026-11-21
- S&P 500 falls 7 days in a row, longest losing streak since February 2020 — Polymarket · 2026-11-21
- New US chip rules reportedly require licenses for non-US fabs and restrict overseas datacenters — JensHonack · 2026-11-21
- Portuguese tutorial walks through running MiniMax H3 locally on PC — Ashamed-Rub5601 · 2026-11-21