16:42
2026-09-01
github.com
ai-tools
Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
Slotstream, a new Swift binary, lets users run the 104 GB Qwen3.8-Flash-Next model on a 48 GB Mac at about 12 tokens per second by streaming weights from SSD, with peak memory of 32 GB and a cold star…