·
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.
| 信号 | 强度 | 权重 | 影响 |
|---|---|---|---|
| Capabilitiesjust now | 50 | 30% | +15.0 |
| Recencyjust now | 90 | 15% | +13.6 |
| Output Capacityjust now | 85 | 15% | +12.8 |
| Context Windowjust now | 81 | 15% | +12.2 |
| Pricingjust now | 30 | 25% | +7.5 |
社区和从业者反馈在基准测试和价格之上增加了真实世界的信号。
Share your experience with gpt-oss-20b (free) and help the community make better decisions.