80 GB accelerator memory
MXFP4 · vLLM / TensorRT-LLM
OpenAI supports a single 80 GB GPU; NVIDIA has also demonstrated it on 128 GB DGX Spark.
OpenAI
Text model
OpenAI's larger open-weight model for advanced reasoning and tools.
Capabilities
The most useful reasons to choose this model, without making you read through its repository first.
Advanced reasoning
Complex agents
Structured tool use
For providers
The provider requirements live here, separate from the information you need to choose and use the model.
80 GB accelerator memory
MXFP4 · vLLM / TensorRT-LLM
OpenAI supports a single 80 GB GPU; NVIDIA has also demonstrated it on 128 GB DGX Spark.
2 accelerators · 80 GB total
MXFP4 · tensor parallel · vLLM
A sharded run depends on the exact approved backend and still needs context headroom.
Source and license
OpenMayhem links back to the source repository so you can inspect the model card, files, license, limitations, and creator guidance directly.