Apple's $899 M6 Mac Mini Is Openly Built for Running LLMs Locally
Scobleizer · x · 2026-08-26
Apple is no longer hiding it: the new Mac Mini with M6, its first 2nm chip, starts at $899 and is pitched for local AI.
- $899 Mac Mini (32GB): comfortably runs Qwen 3.6 27B (near-GPT-4 quality), Qwen 3 Coder 32B as a full desk-side coding assistant, full-precision Llama 4 8B, and DeepSeek R1 32B; LLM processing is 13.5x faster than M1 and 4x faster than M4.
- Mac Studio with M5 Ultra (512GB): runs Llama 4 70B at high-quality quantization, DeepSeek V4 with hundreds of billions of parameters, and frontier-scale models entirely in local memory; four Mac Studios can be clustered over Thunderbolt 5 to run trillion-parameter models locally.
Apple said Mac grew 30% last quarter largely because people are buying these to run AI models on their own desks instead of paying for cloud.
Related event: Apple Launches M6 Mac Mini, Positioning It as a Local AI Machine(14 posts)→
More from Embodied
- Volvo and NVIDIA expand partnership to bring safe automated driving to next-gen cars — nvidia · 2026-10-16
- Tevel's robotic system harvests fruit around the clock using computer vision — LexiLove · 2026-10-16
- SHOES: 10 minutes of real-robot RL lets quadrupeds walk in shoes, CoRL 2026 paper — kscottz · 2026-10-16
- Tesla Cybercab robotaxis logged zero crashes in first two weeks of public rides, NHTSA data shows — elonmusk · 2026-10-16
- Robotics LLMs tested on 16 tasks: GPT-6 Astra hits 17.2% success vs Fable's 9.1% — pabbeel · 2026-10-16
- WEDGE paper generates training environments conditioned on navigation agent failures — _akhaliq · 2026-10-16