{"slug": "inkling-2-mini-runs-on-a-laptop-five-picks-for-running-local-ai", "title": "Inkling 2 Mini runs on a laptop. Five picks for running local AI", "summary": "Thinking Machines Lab, founded by Mira Murati, released Inkling 2 Mini on Nov. 20, an open-weights model with a roughly 20GB footprint that its researchers ran offline on a MacBook Pro. A day earlier, AMD and Unsloth added NPU support to Unsloth Desktop, letting Ryzen AI laptops run local models on their low-power AI engine. The two launches shift the buying question for local AI toward laptop memory capacity during Black Friday week.", "body_md": "# Inkling 2 Mini runs on a laptop. Five picks for running local AI\n\n**Thinking Machines' new open model fits in about 20GB, and AMD just opened Ryzen AI NPUs to Unsloth. Here's the laptop gear with enough memory to run models locally.**\n\n        By [Ryan Merket](https://runtimewire.com/author/ryan-merket)\n        · Published \n\nLaptop-sized AI had a big week. On Nov. 20th, Mira Murati's Thinking Machines Lab released Inkling 2 Mini, an open-weights model with a ~20GB footprint that its researchers ran offline on a MacBook Pro. A day earlier, AMD and Unsloth added NPU support to Unsloth Desktop, so Ryzen AI laptops can run local models on their low-power AI engine.\n\nIf you're shopping Black Friday week, memory is the spec that matters most. Here are five picks that fit these two launches.\n\nQuick picks\n\nWhy memory is the spec to watch…", "url": "https://wpnews.pro/news/inkling-2-mini-runs-on-a-laptop-five-picks-for-running-local-ai", "canonical_source": "https://runtimewire.com/article/inkling-2-mini-runs-on-a-laptop-five-picks-for-running-local-ai", "published_at": "2026-11-22 15:43:42+00:00", "updated_at": "2026-11-22 16:11:51.683906+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-infrastructure"], "entities": ["Thinking Machines Lab", "Mira Murati", "Inkling 2 Mini", "AMD", "Unsloth", "Unsloth Desktop", "Ryzen AI", "MacBook Pro"], "also_reported_by": [], "takeaway": "Inkling 2 Mini is an open-weights model with a ~20GB footprint that Thinking Machines ran offline on a MacBook Pro, and AMD's Unsloth Desktop NPU support lets Ryzen AI laptops run local models on the low-power AI engine.", "recommendation": null, "alternates": {"html": "https://wpnews.pro/news/inkling-2-mini-runs-on-a-laptop-five-picks-for-running-local-ai", "markdown": "https://wpnews.pro/news/inkling-2-mini-runs-on-a-laptop-five-picks-for-running-local-ai.md", "text": "https://wpnews.pro/news/inkling-2-mini-runs-on-a-laptop-five-picks-for-running-local-ai.txt", "jsonld": "https://wpnews.pro/news/inkling-2-mini-runs-on-a-laptop-five-picks-for-running-local-ai.jsonld"}}