Tag: vLLM
-
Poolside’s Laguna S 2.1 118B Punches Above Its Weight
by Chris DePuy / July 28, 2026 This week, the local AI community has been running Poolside’s latest open-weight model, Laguna S 2.1, on everything from single DGX Sparks to 3090 Quad workstations. Released on July 21, Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token, a 1M-token…
-
DeepSeek V4 Flash DSpark on 2× DGX Spark: ~60-67 tok/s with Speculative Decoding
For local inferencing, here is a setup that has proven to be quite stable and fast. It’s the 2x DGX Spark running DeepSeek V4 Flash. It keeps the model running locally and, I’d say, is near Frontier, and doesn’t get lost often when using agents. It’s pretty good at planning, too. The reviews quote ~40…
-
SGLang vs vLLM vs llama.cpp vs Atlas — The Inference Engine Shootout for DGX Spark Clusters
SGLang vs vLLM vs llama.cpp vs Atlas — The Inference Engine Shootout for DGX Spark Clusters The NVIDIA DGX Spark (GB10) has transformed from a curiosity into a genuine building block for local AI infrastructure. What began as a 128GB unified-memory desktop appliance has, through community effort and NVIDIA’s own software maturation, become a node…
-
DGX Spark Clusters by the Numbers: A Sizing Guide Across 1, 2, 3, and 4 Nodes
NVIDIA’s DGX Spark (GB10) started as a deskside curiosity — a 128GB unified-memory workstation drawing ~38W from the GPU during inference. Over the last several weeks, a wave of open-source recipes and community benchmarks has turned the Spark into a modular building block. Users are connecting 2, 3, and 4 units directly — no switch…
-
What You Can Run on a DGX Spark Today (Mid-2026)
A wave of open-source recipes and community benchmarks this week clarified what the deskside AI inference market can do in mid-2026 on NVIDIA DGX Spark hardware.