LocalForge
Retour au guide
MODEL / OPENAI

gpt-oss-120b

OpenAI targets one 80 GB accelerator. Correct serving requires Harmony format support.

Source primaire
Paramètres totaux117B5.1B active / token
Mémoire estimée~80 GBMXFP4
Contexte128KText
LicenseApache-2.0Primarily English
01 / IDÉAL POUR
  • reasoning
  • agents
  • datacenter serving
02 / COMPATIBILITÉ ESTIMÉE
03 / DÉPLOYER AVEC
vLLMAdvancedvllm serve openai/gpt-oss-120b --dtype auto
TensorRT-LLMAdvancedtrtllm-serve openai/gpt-oss-120b
llama.cppMediumllama-server -m /path/to/verified-model.gguf --port 8080
Attention

OpenAI targets one 80 GB accelerator. Correct serving requires Harmony format support.