MODEL / OPENAI

gpt-oss-20b

Model card checked 2026-09-24 · Memory fit estimated; speed unknown unless a separately linked measurement matches your configuration.

Also searched as: gpt-oss:20b

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

Primary source

Total parameters21B3.6B active / token

Estimated memory~16 GBMXFP4

Context128KText

LicenseApache-2.0Primarily English

01 / BEST FOR

reasoning
agents
tool use

02 / ESTIMATED FIT

Mac Studio M5 Ultra · 96 GBComfortable Mac mini M6 · 24 GBTight fit MacBook Pro M5 Max · 64 GBComfortable Framework Desktop · Ryzen AI Max+ 395 · 128 GBComfortable Radeon AI PRO R9700 · 32 GBComfortable

03 / DEPLOY WITH

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.

OllamaEasyollama run gpt-oss:20b

llama.cppMediumllama-server -m /path/to/verified-model.gguf --port 9931

LM StudioEasySearch “openai/gpt-oss-20b” → Load a Q4/INT4 build → Start Server

vLLMAdvancedvllm serve openai/gpt-oss-20b --dtype auto

Watch out

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