12:18
2026-08-11
github.com
large-language-models
Show HN: DeepSeek V4 Flash with 7.7 GiB RAM using NVMe demand paging
Mutaz Abubaker released a research preview of DeepSeek V4 Flash, a 78.62 GiB GGUF model with 284.33B logical parameters, that runs on a Linux laptop with only 7.7 GiB of physical RAM and no GPU using …