A vLLM-XPU and DFlash recipe for Muse Glimmer 30B on a single Intel Arc Pro B70, reporting 278 aggregate tok/s across eight clients and an 840.8 tok/s burst peak at concurrency 96.
GitHub · Local & open models★ Pick· ★ 1
3 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
An OpenAI- and Anthropic-compatible serving stack for Muse Glimmer 30B on one or two Intel Arc Pro B70s, built oracle-first with a float64 CPU reference that gates every GPU kernel.
GitHub · Local & open models
muse-glimmer-intel-serve
A tested Muse Glimmer 30B Q4_K_M serving package for Intel Arc Pro B70 with full 131k context, reporting 19.0 tok/s decode at 129k cached and 503 tok/s full-context prefill.
GitHub · Local & open models
ChatForm
Tgmlabs