carloslfu/slotstream

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.

↗ Abrir no GitHub

Estrelas

287

Bifurcações

16

Linguagem

Swift

Licença

MIT

Último push

há 5 dias

Swift macos llm swift ollama llm-inference local-llm qwen apple-silicon mlx mixture-of-experts

Página inicial do Hacker Newshá 1 semana

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

por carloslfu220 pontos101 comentáriosDiscussão → Repo do GitHub: carloslfu/slotstream