OpenAI's first open-weight release since GPT-2. Matches o4-mini on AIME and MMLU despite being open. Proves that open-weight frontier quality is achievable — a landmark for the local AI community.
This model requires a specialized High-VRAM environment. Ensure you have the latest CUDA Drivers or Metal Framework installed.
Minimum VRAM: 82GB VRAM Recommended
The GPT-OSS 120B model by OpenAI is a 117B (MoE) parameter architecture optimized for reasoning tasks. It requires approximately 80GB of VRAM to comfortably run locally using a Q4_K_M quantization. Extending the context window up to 131,072 tokens will dynamically allocate further VRAM, meaning high-bandwidth memory hardware is strictly advised.
For running GPT-OSS 120B at maximum tokens-per-second, we recommend using LM Studio or Ollama with a GGUF quantization (Q4_K_M or Q6_K). If you are multi-GPU, use vLLM to distribute the layers across your VRAM pool for optimal throughput.
You will need a GPU with at least 82GB of VRAM to run the Q4_K_M quantized version smoothly with a moderate context window.
The simplest method is utilizing Ollama by executing 'ollama run gpt-oss:120b' directly in your command line. Alternatively, you can search for the model via LM Studio's interface.