Can I run this LLM?
Can a NVIDIA DGX Spark (GB10, 128GB) run GLM-4.7 Flash (MoE)?
GLM · MIT · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Best fit: GLM-4.7 Flash (MoE) at FP16 · 59.9 GB · 24–37 tok/s on a NVIDIA DGX Spark (GB10, 128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 9.7 GB | 74–111 tok/s | Runs great |
| Q3_K_M | 12.9 GB | 66–98 tok/s | Runs great |
| Q4_K_M | 18.2 GB | 55–83 tok/s | Runs great |
| Q5_K_M | 21.3 GB | 50–76 tok/s | Runs great |
| Q6_K | 24.7 GB | 46–69 tok/s | Runs great |
| Q8_0 | 31.8 GB | 39–59 tok/s | Runs great |
| FP16 | 59.9 GB | 24–37 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA DGX Spark (GB10, 128GB) runsGLM-4.7 Flash (MoE) on other machinesWhat to buy to run it →
Ran GLM-4.7 Flash (MoE) on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →