model-streaming

Tag

Cards List
#model-streaming

Janas: Run LLMs larger than RAM by streaming experts from SSD

Hacker News Top ↗ · 5d ago Cached

Janas 是一个开源工具,通过从 SSD 流式加载专家模型(mixture-of-experts),让内存小于模型体积的笔记本也能运行 LLM。在 32GB 内存的笔记本上,Qwen3-Next-80B(48GB)推理速度达 37 tok/s,显著超越 llama.cpp 的 2.8 tok/s。

0 favorites 0 likes
#model-streaming

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

Hacker News Top ↗ · 2026-09-01 Cached

slotstream is an open-source tool that enables running large AI models like Qwen3.8-Flash-Next on Macs with limited memory by streaming model weights from SSD, achieving approximately 12 tokens per second on a 48GB Mac.

0 favorites 0 likes
← Back to home

Submit Feedback