Can I run this LLM?
Can a NVIDIA RTX 5080 (16GB) run GPT-OSS 20B (MoE)?
GPT-OSS · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.
Yes — it runs great.
Best fit: GPT-OSS 20B (MoE) at Q5_K_M · 11.7 GB · 171–256 tok/s on a NVIDIA RTX 5080 (16GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 11.5 GB | 173–259 tok/s | Runs great |
| Q3_K_M | 11.5 GB | 172–258 tok/s | Runs great |
| Q4_K_M | 11.6 GB | 171–257 tok/s | Runs great |
| Q5_K_M | 11.7 GB | 171–256 tok/s | Runs great |
| Q6_K | 12.0 GB | 169–253 tok/s | Tight / slow |
| Q8_0 | 12.1 GB | 168–252 tok/s | Tight / slow |
| FP16 | 13.8 GB | 157–236 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 5080 (16GB) runsGPT-OSS 20B (MoE) on other machinesWhat to buy to run it →
Ran GPT-OSS 20B (MoE) on a NVIDIA RTX 5080 (16GB)? Add your real numbers →