antirez runs local LLM tests on Mac Studio M3 Ultra with 512GB RAM
antirez · x · 2026-09-12
Redis creator antirez reports that running models locally on a Mac Studio M3 Ultra with 256GB of RAM "works well, as expected," and that his full residency tests were done on a 512GB unit provided via SSH by friends — further evidence that big-memory Apple Silicon is a practical local LLM inference platform.
More from Infra
- effect-harness on Cloudflare: run agent loops, tools and credentials on separate VMs — samgoodwin89 · 2026-10-31
- Google's Project Suncatcher boots TPU in orbit and beams back first AI response — sundarpichai · 2026-10-31
- Together AI launches Post-Training platform for agentic RL with tool-use environments — togethercompute · 2026-10-31
- General Compute raises $100M for inference capacity as CoreWeave stock hits 12-month low — YvesMulkers · 2026-10-31
- Analyst warns of unstable AI compute feedback loop as Kioxia's NAND price warning triggers flash crash — bookwormengr · 2026-10-31
- SOMA launches enterprise prompt-compression layer claiming 20%+ inference savings — markjeffrey · 2026-10-31