openai

gpt-oss-120b

OpenAI's 117B-parameter (5.1B active) open-weight reasoning model, built to fit a single 80GB GPU through MXFP4 quantization.text generationapache-2.02.4M downloadsHugging Face

Cheapest GPU in stock that fits

A single GPU with at least 80 GB for inference.

NosanaIn stock · 21 freeStart right away

1× RTX PRO 600096 GB VRAM

Nosana network, hosts worldwide

Details

Stock and price checked 16 min ago.

Self-service: you start it yourself, with no order or sales contact.

Confidential computing: data stays encrypted while the GPU works on it, so the host can't read it.

nvidia-pro-6000-cc

Full price

€2.09

per hour, whole instance, 1 GPU

View offer

GPU memory it needs

From model cards and vendor documentation. Lower precision needs less memory, with slightly lower quality. Estimates are marked.

What you want to do	Precision	Minimum	Setup	Basis
Run the model Model card states the MXFP4 checkpoint runs on a single 80GB GPU; the vLLM recipe lists a 96 GB minimum for the same checkpoint while describing it as fitting 1x A100 80GB. Card also says it can be fine-tuned on a single H100 node, with no GB figure.	4-bit	80 GB	1x H100 or MI300X (80 GB, per model card)	Published