Aller au contenu principal
buildradar
Se connecter

carloslfu/slotstream

@carloslfu

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.

Étoiles
287
Bifurcations
16
Langage
Swift
Licence
MIT
Dernier push
il y a 6 jours
Swiftmacosllmswiftollamallm-inferencelocal-llmqwenapple-siliconmlxmixture-of-experts