deepseek-v4.1POST
双 DGX Spark 本地跑 V4.1 Flash 等三个模型的仓库
用户列出在 2 台 DGX Spark 上本地部署的三个模型仓库，含 DeepSeek V4.1 Flash-1017，目前还在跑 16GB 的 Qwen3.8-EXL3。
William Rodriguez - Analytical Ants
@wmRod_AA11 天前收录原推发布于 2026.10.20
William Rodriguez - Analytical Ants @wmRod_AA原推发布于 2026.10.20
Top three I've settled on (2x DGX Sparks) * https://github.com/MiaAI-Lab/DeepSeek-v4.1-Flash-1017-2x-DGX-Sparks * https://github.com/MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold * https://github.com/MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold All @MiaAI_lab , super excited to get started with STRONG local AI (currently running a 16Gb Qwen3.8-EXL3 😅)
这条是引用着另一条写的：x.com/wmrod_aa/status/2112238777783713969
x.com/wmrod_aa/status/2112259610820374559采集于 2026.10.20 12:05