OpenAI: gpt-oss-20b
OpenAIllm
Published August 5, 2025
About
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.
Try OpenAI: gpt-oss-20b
Test this model in the Sandbase Playground with your own prompts.
Open in Playground