MODEL / OPENAI
gpt-oss-20b
Use a runtime that applies OpenAI's Harmony response format. Active parameters are not the memory-fit number.
一手來源總參數21B3.6B active / token
估算記憶體~16 GBMXFP4
上下文128KText
LicenseApache-2.0Primarily English
01 / 適合
- reasoning
- agents
- tool use
02 / 估算適配
03 / 部署方式
OllamaEasy
ollama run gpt-oss:20bllama.cppMedium
llama-server -m /path/to/verified-model.gguf --port 8080LM StudioEasy
Search “openai/gpt-oss-20b” → Load a Q4/INT4 build → Start ServervLLMAdvanced
vllm serve openai/gpt-oss-20b --dtype auto注意
Use a runtime that applies OpenAI's Harmony response format. Active parameters are not the memory-fit number.