Can I run this LLM?
Can a NVIDIA L40S (48GB) run Ornith 1.5 9B?
Ornith · MIT · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Ornith 1.5 9B at FP16 · 17.9 GB · 32–48 tok/s on a NVIDIA L40S (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 4.1 GB | 108–161 tok/s | Runs great |
| Q3_K_M | 4.9 GB | 94–141 tok/s | Runs great |
| Q4_K_M | 5.9 GB | 82–123 tok/s | Runs great |
| Q5_K_M | 6.9 GB | 73–110 tok/s | Runs great |
| Q6_K | 7.7 GB | 67–100 tok/s | Runs great |
| Q8_0 | 9.6 GB | 56–84 tok/s | Runs great |
| FP16 | 17.9 GB | 32–48 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA L40S (48GB) runsOrnith 1.5 9B on other machinesWhat to buy to run it →
Ran Ornith 1.5 9B on a NVIDIA L40S (48GB)? Add your real numbers →