Can I run this LLM?
Can a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) run GLM-5.3 Flash (MoE)?
GLM · MIT · estimated for a 288.0 GB machine at 4K context.
Yes — it runs great.
Best fit: GLM-5.3 Flash (MoE) at Q8_0 · 341.5 GB · 46–69 tok/s on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 125.7 GB | 254–381 tok/s | Runs great |
| Q3_K_M | 155.0 GB | 237–356 tok/s | Runs great |
| Q4_K_M | 200.8 GB | 215–323 tok/s | Runs great |
| Q5_K_M | 243.7 GB | 198–297 tok/s | Runs great |
| Q6_K | 281.0 GB | 103–155 tok/s | Runs great |
| Q8_0 | 341.5 GB | 46–69 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) runsGLM-5.3 Flash (MoE) on other machinesWhat to buy to run it →
Ran GLM-5.3 Flash (MoE) on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB)? Add your real numbers →