0xSero /
DeepSeek-V4.1-Flash-Two-Sparks
DeepSeek-V4.1-Flash on two DGX Sparks: EXL3 routed experts, 262k context, 2M-token KV, vision, tools, MTP, bundled with Pi
Updated 43 min ago
+1 stars gained this week
Stars gained each day, last 30 days
Oct 4Oct 19Today
This week Before
In short
Scripts to serve the DeepSeek-V4.1-Flash model across two NVIDIA DGX Spark nodes using vLLM, with EXL3-quantized experts, and to use it from the Pi coding agent. Intended for users running DGX Spark hardware.
Summary written by AI from the repository’s description and README.
0xSero / DeepSeek-V4.1-Flash-Two-Sparks
View on GitHub(opens in new tab)