今天新增deepseek-v4.1POST
在原生 llama.cpp 上本地跑 748B 的 DeepSeek V4.1 Flash
用户称用原版 llama.cpp 跑起 748B 的 DeepSeek V4.1 Flash 本地构建，并放出 GSQ-RCO 上游 GGUF 量化权重链接。
vveerrgg
@vveerrgg10 小时前收录原推发布于 2026.10.28
vveerrgg @vveerrgg原推发布于 2026.10.28
Flowers to @Chaos2Cured 🌸 If Wednesday really is *the day* the internet breaks; at least I learned to roll my own local build of DeepSeek V4.1 on stock llama.cpp. I’ve got a 748B model running locally. Even if this post might age like milk... https://huggingface.co/HumanjavaEnterprises/DeepSeek-V4.1-Flash-1017-GSQ-RCO-upstream-GGUF
x.com/vveerrgg/status/2115227532714983492采集于 2026.10.28 12:02