SGLang
@sgl_project
SGLang is honored to provide day-0 support for @AIatMeta's Muse Glimmer. ~230 tok/s on a single RTX 5090 with NVFP4 + DFlash on, and it runs out of the box on @NVIDIAAI RTX PRO 6000, DGX Spark, and Apple Silicon via MLX. Huge thanks to the NVIDIA and Meta teams for the
X post · Local & open models· ♥ 95
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.
Shown every 12 builds · on every catalog page
LMSYS Org
@lmsysorg
@AIatMeta's Muse Glimmer (30B dense, open-weights) launches with SGLang day-0 support. We got ~230 tok/s on a single RTX 5090, with NVFP4 + DFlash on. It also works out of the box on @NVIDIAAIDev RTX Pro 6000, DGX Spark, and MLX for Mac. Speed and reliability have always been
X post · Local & open models· ♥ 129
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
Meta's launch post for Muse Glimmer, an Apache 2.0 30B model for local agents that fits in ~20GB at 4-bit and runs on M4/M5 Max Macs, RTX 5090s or 24–32GB GPUs.
Resource · Local & open models
Mixed-precision NVFP4/MXFP8 checkpoint of Muse Glimmer packed for SGLang, keeping v_proj, down_proj and lm_head at MXFP8.
Resource · Local & open models· ♥ 9
The smallest and fastest MLX 4-bit (group size 64) Muse Glimmer checkpoint, served with SGLang's MLX backend on Macs with 48 GB+ unified memory.
Resource · Local & open models· ♥ 11
Tested SGLang and vLLM launch recipes for an NVFP4 export of a Hermes-agentic fine-tune of Muse-Glimmer-30B on NVIDIA DGX Spark (GB10).
GitHub · Local & open models
Benchmark reports on Muse-Glimmer-30B on NVIDIA DGX Spark covering BF16 to Q4 to DFlash (a 10x speedup) and NVFP4 via SGLang, plus a head-to-head against Qwen3.6-27B.
GitHub · Benchmarks & research
Meta's official Muse-Glimmer-30B repo: ~29.6B dense model with a 1.8B vision encoder, 131K context, Apache 2.0, with vLLM and SGLang serve commands.
Site · Local & open models
9 builds · page 1 of 1
