LocalForge
Wróć
MODEL / OPENAI

gpt-oss-120b

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

Źródło pierwotne
Wszystkie parametry117B5.1B active / token
Szacowana pamięć~80 GBMXFP4
Kontekst128KText
LicenseApache-2.0Primarily English
01 / NAJLEPSZY DO
  • reasoning
  • agents
  • datacenter serving
02 / SZACOWANE DOPASOWANIE
03 / URUCHOM PRZEZ
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
Uwaga

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