Назад
MODEL / OPENAI

gpt-oss-20b

Use a runtime that applies OpenAI's Harmony response format. Active parameters are not the memory-fit number.

Первичный источник
Всего параметров21B3.6B active / token
Оценка памяти~16 GBMXFP4
Контекст128KText
LicenseApache-2.0Primarily English
01 / ЛУЧШЕ ВСЕГО
  • reasoning
  • agents
  • tool use
02 / ОЦЕНКА СОВМЕСТИМОСТИ
03 / ЗАПУСК ЧЕРЕЗ
OllamaEasyollama run gpt-oss:20b
llama.cppMediumllama-server -m /path/to/verified-model.gguf --port 8080
LM StudioEasySearch “openai/gpt-oss-20b” → Load a Q4/INT4 build → Start Server
vLLMAdvancedvllm serve openai/gpt-oss-20b --dtype auto
Внимание

Use a runtime that applies OpenAI's Harmony response format. Active parameters are not the memory-fit number.