Expired80% confidenceFactTime unknown

GPT-OSS 120B performance is on par with O4 mini.

1

Sources

80%

Confidence

Medium-term (~90 days)

Relevance

6/1/2026

First Seen

This claim has expired. It is kept for the record and no longer describes the current state.

Valid until: 8/30/2026(expired)

Sources

OpenAI Open-Sources GPT-OSS: Run O4-Level Models on 16GB VRAM — Complete Deployment Guide

bilibili九天Hector

Related Entities

GPT-OSS 120Bmodel O4 minimodel

Related Claims

Unverified单卡RTX 4090即可运行GPT-OSS 20B，单卡A100即可运行GPT-OSS 120B73% similar UnverifiedGPT-OSS-120B officially requires no less than 60GB of VRAM.73% similar UnverifiedGPT-OSS 120B surpasses the performance of the Qwen3 235B AR2B reasoning model with less than half the parameter count and hardware cost.71% similar UnverifiedGPT-OSS 120B需要大于80GB显存（如H100 GPU）才能运行71% similar UnverifiedGPT-OSS 20B推理仅需16G显存，微调仅需24G显存70% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/23213

API

curl https://kongchang.com/api/v1/knowledge/claims/23213

MCP

get_claim(id=23213)