antirez runs DeepSeek v4.1 Flash locally on a 128GB M5 Max, SSD streaming surprisingly fast
antirez · x · 2026-09-11
antirez demonstrated DeepSeek v4.1 Flash running locally via DwarfStar on a 128GB M5 Max, with SSD-based expert streaming delivering surprisingly fast inference. He credits recent SSD streaming changes that retain the right experts, and possibly DS4.1 reusing the same experts more. He plans to open QA online when ready.
More from Infra
- Musk: robot RAM demand will dwarf everything else, and 100% of superintelligence compute goes to deep space — elonmusk · 2026-10-27
- RTX 5090 hits $7K as PC gaming community goes into 'denial' over AI boom — PAstynome · 2026-10-27
- Wan2GP lands on Pinokio: 1-click AI video on 6GB GPUs — cocktailpeanut · 2026-10-27
- Wan2GP AMD one-click installer lands on Pinokio, runs AI video on 6GB VRAM — cocktailpeanut · 2026-10-27
- AWS on agent prompt caching: explicit + implicit patterns to slash token costs — AWS ML Blog · 2026-10-27
- Thieves spoofing GPS steal $100M+ in data center cargo since June — Ars Technica AI · 2026-10-27