← Back to events
ActiveTech

Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s

Photo: Hacker News

What happened

Run Qwen3.8-Flash-Next (125B MoE, 104 GB at 4-bit) on Macs with a fraction of that RAM by streaming experts from SSD. MLX + Swift, Ollama-compatible API. - carloslfu/slotstream

Summary assembled by rule from the sources below

Why it's spreading

Sources