Autor: Jakub Rusinowski · Ostatnia aktualizacja: 15 sierpnia 2026
Yes. GPT-OSS 20B needs 10.6 GB at MXFP4 and the NVIDIA A100 80GB has 80 GB, leaving about 69.4 GB of headroom, at roughly 89 tok/s (estimated) with room for up to 128K of context.
| Model | GPT-OSS 20B |
| Parameters | 20B |
| Quantization | MXFP4 |
| VRAM needed | 10.6 GB |
| NVIDIA A100 80GB VRAM | 80 GB |
| Verdict | Runs |
| Max context | 128K |
| Estimated speed | ~89 tok/s |
Nothing to change — run it at MXFP4. If you want more capability, check whether the next size up also fits.
Running GPT-OSS 20B on this card:
At 2 hrs/day, buying (~$15,000) beats renting at $0.34/hr after about 61.3 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
All GPT-OSS sizes on the NVIDIA A100 80GB | VRAM calculator for GPT-OSS 20B | NVIDIA A100 80GB GPU page | Check your hardware