Can I run this LLM?
Can a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) run Muse Glimmer 30B?
Muse · Apache 2.0 · estimated for a 288.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Muse Glimmer 30B at FP16 · 55.7 GB · 82–123 tok/s on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 11.0 GB | 217–325 tok/s | Runs great |
| Q3_K_M | 14.0 GB | 196–293 tok/s | Runs great |
| Q4_K_M | 17.3 GB | 176–264 tok/s | Runs great |
| Q5_K_M | 20.1 GB | 163–244 tok/s | Runs great |
| Q6_K | 23.4 GB | 149–224 tok/s | Runs great |
| Q8_0 | 29.6 GB | 129–193 tok/s | Runs great |
| FP16 | 55.7 GB | 82–123 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) runsMuse Glimmer 30B on other machinesWhat to buy to run it →
Ran Muse Glimmer 30B on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB)? Add your real numbers →