Muse 30B Glimmer
on 2× NVIDIA DGX Spark · llama.cpp · 1,000,000 ctx
Sep 7, 2026
Use cases
long-contextagenticcodingvision
Summary
User reports retrieval at 832K tokens with 3/3 success.
DFlash speculative decoding gives roughly 3x speedup.
RPC split is slower than single-node.