OpenAI has released two new open-weight language models under the permissive Apache 2.0 license. These models are designed to deliver strong real-world performance while running on consumer hardware, including a model that can run on a high-end laptop with only 16 GB of GPU.
Real-World Performance at Lower Hardware Cost
The two models are:
- gpt-oss-120b (117 billion parameters)
- gpt-oss-20b (21 billion parameters)
The larger gpt-oss-120b model matches OpenAI’s o4-mini on reasoning benchmarks while requiring only a single 80GB GPU. The smaller…








