BREAKING
Laguna Runs on NVIDIA DGX Spark
0$
price class
0GB
unified memory
0PFLOPS
FP4 AI perf
Local and Hosted Laguna Models
Laguna XS.2Apache 2.0
33B MoE, ~3B active
Local agentic coding
Runs on single devices
Laguna M.1API
225B MoE, ~23B active
256K context window
NVFP4 quantization
Laguna-XS-2.1 Throughput on Spark
Q4_K_M117
Q8_0 GGUF52
NVFP4 256K42
Software Stack Still Maturing
Agentic Coding Moves Local
AI NEWS BLITZ
Poolside says its next Laguna coding model runs locally on NVIDIA's DGX Spark desktop.