From 16GB to 128GB: why a daily frontier-AI user is still buying a Mac Studio for local models
TheOyinbooke · x · 2026-09-29
Despite using frontier AI daily, the author is buying a Mac Studio—and the numbers explain why: on a 16GB Mac Mini M4, loading a 3GB model already pushes the system to 14.24GB used with 4.93GB in swap, limiting you to 3B-8B models. His entire local library sat untouched for 172 days. 16GB was never a workhorse, just a window.
Related event: Why a heavy AI user scaled from 16GB to 128GB for local models(2 posts)→
More from Infra
- Macrocosmos launches iota SDK and Liquid Compute to train on disaggregated global compute — markjeffrey · 2026-09-29
- "Got into datacenters for crypto, making 10000x more in AI" — industry quip — wordgrammer · 2026-09-29
- Starship launch just added ~1% to global internet bandwidth, investors say world isn't pricing it in — juanbenet · 2026-09-29
- GPU shortage: B700 unavailable, RTX 5090 listings hit $10,000 — Dismal-Effect-1914 · 2026-09-29
- Disaggregated Quantization Boosts 1-bit LLM Accuracy by 32+ Points and TTFT by 1.78x — ISTA-DASLab · 2026-09-29
- New GPU Prices API Tracks Real-Time H100/B200 Rental Rates via REST or MCP — virattt · 2026-09-29