gpt-oss-120b / 20b
gpt-oss-120b / 20b — Apache 2.0, native MXFP4
Why it matters
OpenAI's first open-weight language models since GPT-2; 120b (117B total, 5.1B active per token) runs on a single 80 GB GPU, and 20b (21B total, 3.6B active) within 16 GB of memory
Source — Primary sources first; secondary reports are labelled “Press”
Officialopenai.comhttps://openai.com/index/introducing-gpt-oss/Added in Week 35, 2026 · See that week