An Apache-2.0 template for Meta Muse connectors with per-connection tokens, async job scaffolding and a single registry that generates routes, OpenAPI and llms.txt, deployable to Vercel, Workers or Docker.
Skill · Connectors & MCP
5 builds · page 1 of 1
Your product
Sponsored
Put your logo, a line of copy and an image right here, between the builds Muse developers come to read. Same size as a post.
Put your product here
Shown every 12 builds · on every catalog page
NVIDIA's technical blog reports Muse Glimmer serving over 20K tokens/sec on a single Blackwell Ultra GPU and covers RTX 5090, DGX Spark, DGX Station and Jetson deployments.
Resource · Local & open models
Run local agentic workflows with Muse Glimmer on NVIDIA
A measured deployment report of Muse Glimmer 30B NVFP4 with DFlash on a single Dell Pro Max GB10, where it posted top vision and SRE-ops scores but failed five deployment gates against DeepSeek V4 Flash.
GitHub · Local & open models
Muse Glimmer on Dell GB10: a negative result
Ryan | Intelligence Engineer
@RyanIntEngineer
I just built and validated a complete Muse Glimmer deployment for one DGX Spark. I didn’t make another quant—I integrated the available pieces into a pinned, verified, DFlash-accelerated, tool-capable, reboot-durable stack that actually works in OWUI.
X post · Local & open models· ♥ 4
Reboot-durable Glimmer stack on DGX Spark
A reproducible single-GPU deployment of Muse Glimmer 30B in BF16 with DFlash speculative decoding on a 96GB RTX PRO 6000 Blackwell, served via vLLM with pinned overlays and smoke tests.
GitHub · Local & open models
ChatForm
Tgmlabs