Saltar al contenido principal
buildradar
Sign in

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.

Estrellas
287
Bifurcaciones
16
Lenguaje
Swift
Licencia
MIT
Último push
hace 2 días
Swiftmacosllmswiftollamallm-inferencelocal-llmqwenapple-siliconmlxmixture-of-experts