Written by Jakub Rusinowski · Last updated September 19, 2026
Model library → Muse Glimmer → Muse Glimmer 30B
Text and image in, 128K context, Apache-2.0. Meta targets a 24 GB card with the 4-bit build; the Ollama tag is an 18 GB quantised download. Grouped-query attention keeps the KV cache small for its size.
Muse Glimmer 30B needs about 19 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
| Parameters | 29.6 Billion |
| Context window | 131,072 |
| Architecture | Dense + perception encoder |
| Provider | Meta (Superintelligence Labs) |
| Licence | Apache 2.0 |
| Specified at | Q4_K_M |
| System RAM | 32 GB |
| Record updated | 2026-09-19 |
Corroborated — Two or more independent sources agree on these figures, but the model card itself was not retrieved. Treat the numbers as good rather than confirmed.
Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
Modelled on a reference NVIDIA RTX 4090 (24 GB). Weights plus framework overhead only — this model publishes no architecture we can read, so no KV cache is included. A real session needs more; the figure is a floor, not a target. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Bits/weight | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|---|
| Q2_K | 2.63 | 9.7 GB | 10.5 GB | ~61 tok/s (est.) | Fits comfortably |
| Q3_K_M | 3.41 | 12.6 GB | 13.4 GB | ~50 tok/s (est.) | Fits comfortably |
| Q4_K_M | 4.83 | 17.9 GB | 18.7 GB | ~37 tok/s (est.) | Fits comfortably |
| Q5_K_M | 5.67 | 21 GB | 21.8 GB | ~32 tok/s (est.) | Tight fit |
| Q6_K | 6.56 | 24.3 GB | 25.1 GB | ~4 tok/s (est.) | Offloads to system RAM (slow) |
| Q8_0 | 8.50 | 31.5 GB | 32.3 GB | ~3 tok/s (est.) | Offloads to system RAM (slow) |
| F16 | 16.00 | 59.2 GB | 60 GB | — | Won't fit |
Want to set your own context length and KV-cache quantization? Use the interactive VRAM calculator.
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
The cheapest catalogued GPU that runs Muse Glimmer 30B is the AMD Radeon RX 7900 XT (20 GB).
Install Ollama, then run:
ollama run muse-glimmer:30bWeights on Hugging Face: meta-models/muse-glimmer.
Best for: agents, tool calling, vision, local assistant.
← All Muse Glimmer models | VRAM calculator | Check your own hardware