Новый проект
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.
- Stars
- ★ 89
- Forks
- ⑂ 4
- Язык
- Swift
- Статус
- В канале 1 янв. 1 г.
AI-разбор
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.