Written by Jakub Rusinowski · Last updated September 19, 2026
Meta's return to open weights, and its first since Llama 4. A 29.6B dense model distilled from the closed Muse Spark, with its own perception encoder, built specifically for agentic work on one consumer card: multi-step reasoning, tool use and failure recovery in a single checkpoint that runs with no network access.
| Licence | What it permits | Applies to |
|---|---|---|
Apache-2.0 | Commercial use permitted Commercial use permitted. No usage restrictions beyond attribution. | Muse Glimmer 30B |
| Muse Glimmer 30B | Min 19 GB VRAM · Q4_K_M · 131,072 ctx · ollama run muse-glimmer:30b |
The cheapest GPU that runs Muse Glimmer locally (min 19 GB VRAM) is the AMD Radeon RX 7900 XT (20 GB).
Install Ollama then run: ollama run muse-glimmer:30b
Minimum VRAM: 19 GB. For best results use Q4_K_M quantization.
Muse Glimmer needs about 19 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Muse Glimmer 30B (19 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — Muse Glimmer runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
Q4_K_M is the best balance of quality and VRAM for Muse Glimmer in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Install Ollama, then run: ollama run muse-glimmer:30b. This downloads Muse Glimmer and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.