16 GB memory
MXFP4 · vLLM / llama.cpp
This is OpenAI's supported minimum. Expect limited context or concurrency near the boundary.
OpenAI
Text model
OpenAI's smaller open-weight reasoning model for tools and agents.
Capabilities
The most useful reasons to choose this model, without making you read through its repository first.
Reasoning assistants
Function calling
Agent workflows
For providers
The provider requirements live here, separate from the information you need to choose and use the model.
16 GB memory
MXFP4 · vLLM / llama.cpp
This is OpenAI's supported minimum. Expect limited context or concurrency near the boundary.
24 GB system RAM
MXFP4 · llama.cpp
Memory fits through CPU/RAM, but a paid provider must verify that throughput is useful.
24 GB memory for headroom
MXFP4 · vLLM / llama.cpp
OpenAI's 16 GB minimum loads the model; 24 GB leaves more room for context and requests.
Source and license
OpenMayhem links back to the source repository so you can inspect the model card, files, license, limitations, and creator guidance directly.