Article URL: https://huggingface.co/spaces/LocalLLaMA/data-inventor
Comments URL: https://news.ycombinator.com/item?id=49941556
Points: 1
source & further reading
huggingface.co — original article
Running 176B Qwen3.8-Flash-Next and 284B DeepSeek-V4 on 32GB/64GB CPU RAM (0 GPUs) with llama-modchip v3.0
Local LLM generation on a consumer GPU: layer-streamed Qwen3.5 inference
An AI app for Android: cloud and local models, SSH, MCP, and screen control