Muse Glimmer 30B VRAM requirements
Meta · 29.6B params · Apache 2.0. Estimates, not vendor numbers.
Muse Glimmer 30B (29.6B parameters) needs about 19 GB of VRAM or unified memory at Q4, 23 GB at Q5 and 33 GB at Q8 (weights plus about 1.5 GB headroom, our estimate). The smallest common setup that runs it is 24GB GPU (RTX 4090).
| Quant | Download | Memory needed |
|---|---|---|
| Q4 | 18 GB | 19 GB |
| Q5 | 21 GB | 23 GB |
| Q8 | 31 GB | 33 GB |
Will it run on my machine?
| Setup | Runs? | Speed est. |
|---|---|---|
| 8GB GPU (RTX 4060) | No | n/a |
| 12GB GPU (RTX 3060 / 4070) | No | n/a |
| 16GB GPU (RTX 4060 Ti 16GB) | No | n/a |
| 24GB GPU (RTX 4090) | Yes, Q5 | ~29 tok/s |
| 32GB GPU (RTX 5090) | Yes, Q5 | ~51 tok/s |
| Mac 16GB (M4) | No | n/a |
| Mac 48GB (M4 Pro) | Yes, Q4 | ~9 tok/s |
| Mac 128GB (M4 Max) | Yes, Q5 | ~16 tok/s |
| PC, 32GB RAM, no GPU | No | n/a |
Best quant that fits each setup, with estimated generation speed from memory bandwidth. Real speed depends on the runtime, context length and settings.
Dense 29.6B including a 1.8B vision encoder. Meta's 4-bit builds target 24GB to 32GB of VRAM.
FAQ
How much VRAM does Muse Glimmer 30B need?
About 19 GB at Q4, 23 GB at Q5 and 33 GB at Q8, including about 1.5 GB headroom. These are estimates from the parameter count on the official model card.
Can Muse Glimmer 30B run on 8GB of VRAM?
Not fully on the GPU. At Q4 it needs about 19 GB; partial CPU offload works but is much slower.
Can Muse Glimmer 30B run on a Mac?
Yes. Mac 48GB (M4 Pro), Mac 128GB (M4 Max) can run it.
Which quant of Muse Glimmer 30B should I use?
Use the highest quant that fits with room to spare: Q8 is near full quality, Q5 is a good balance, and Q4 is the smallest that usually keeps quality acceptable.
Similar-size models
Gemma 4 26B A4B (25.2B) · Qwen3.6 27B (27B) · Qwen3.8 27B (27.8B) · Qwen3 Coder 30B A3B (30.5B) · Gemma 4 31B (30.7B) · DeepSeek R1 Distill Qwen 32B (32.8B)