Can I run this LLM?
Can a NVIDIA RTX 4090 (24GB) run GLM-4 9B?
GLM · MIT · estimated for a 24.0 GB machine at 4K context.
Yes — it runs great.
Best fit: GLM-4 9B at Q8_0 · 10.0 GB · 61–92 tok/s on a NVIDIA RTX 4090 (24GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 4.0 GB | 120–180 tok/s | Runs great |
| Q3_K_M | 5.0 GB | 104–156 tok/s | Runs great |
| Q4_K_M | 6.2 GB | 89–133 tok/s | Runs great |
| Q5_K_M | 7.1 GB | 81–121 tok/s | Runs great |
| Q6_K | 8.3 GB | 71–107 tok/s | Runs great |
| Q8_0 | 10.0 GB | 61–92 tok/s | Runs great |
| FP16 | 18.8 GB | 35–53 tok/s | Tight / slow |
Open the full calculator →Everything a NVIDIA RTX 4090 (24GB) runsGLM-4 9B on other machinesWhat to buy to run it →
Ran GLM-4 9B on a NVIDIA RTX 4090 (24GB)? Add your real numbers →