gpt-oss-120b

OpenAI · gpt-oss
Create a neuronet with this model →
LLMApache-2.0publicTrusted117B params

117B MoE in native MXFP4: one 80 GB GPU.

117B MoE in native MXFP4: one 80 GB GPU.

At a glance

  • Task: LLM (InferenceV1)
  • Params: 117B
  • License: Apache-2.0 (commercial use OK)
  • Hardware: 72 GB+ VRAM
  • dtype: Mxfp4