MODEL / OPENAI

gpt-oss-120b

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

1차 출처

총 파라미터117B5.1B active / token

추정 메모리~80 GBMXFP4

컨텍스트128KText

LicenseApache-2.0Primarily English

01 / 추천 용도

reasoning
agents
datacenter serving

02 / 추정 적합도

Framework Desktop · Ryzen AI Max+ 395 · 128 GB여유 있음 NVIDIA DGX Spark · 128 GB여유 있음 Mac Studio M3 Ultra · 256 GB여유 있음

03 / 배포 환경

These are runtime examples, not validated installation recipes. Fit estimates assume quantized files; official repositories may hold full-precision weights. MLX, GGUF and TensorRT require matching conversions or engines.

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 9931

SGLangAdvancedpython3 -m sglang.launch_server --model-path openai/gpt-oss-120b --port 30000

주의

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