Muse Glimmer 30B assistant
Muse Glimmer 30B assistant is an open-weights language model from Meta, released August 9, 2026. It has 30B parameters (dense). The context window is 128K tokens.
Check it against your own PC →
Can you run Muse Glimmer 30B assistant locally?
The smallest common GPU it runs on is 12 GB of VRAM (with 32 GB of RAM): Q3_K_M, split GPU / CPU, roughly 5 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Very slow | IQ3_XXS (noticeable loss) | 5.2 GB | 6.9 GB | ~4 |
| 8 GB VRAM | Very slow | IQ3_XXS (noticeable loss) | 7.2 GB | 4.9 GB | ~5 |
| 12 GB VRAM | Runs, slowly | Q3_K_M (okay) | 11.2 GB | 4.1 GB | ~5 |
| 16 GB VRAM | Runs on GPU | IQ3_XXS (noticeable loss) | 12.1 GB | – | ~25 |
| 24 GB VRAM | Runs on GPU | Q5_K_M (excellent) | 22.0 GB | – | ~26 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 25.2 GB | – | ~42 |
Ready-made quantizations on Hugging Face: turboderp/Muse-Glimmer-30B-assistant-exl3
Benchmark results
Epoch AI has not published results for Muse Glimmer 30B assistant yet. New models are usually evaluated within days to weeks.
Links
Hugging Face: meta-models/Muse-Glimmer-30B-assistant
More from Meta
Muse Ember · Muse Spark Open · Muse Wonder · Muse Wonder Full · Muse Spark 1.3 · Muse Spark 1.3 Contributor · Muse Glimmer · Muse Spark 1.2