OpenAIGptOss20B

OpenAI GPT-OSS 20B - Efficient Mixture-of-Experts model for speed-sensitive applications

Features:

  • 128K context window

  • MoE architecture: 21B total params, 3.6B active per token

  • Runs on edge devices with 16 GB memory

  • Structured output support

  • Matches o3-mini performance

Important: This model requires the Bedrock Converse API (apiMethod = BedrockAPIMethod.Converse).

See also