GPUs tracked39Price history3 dayssince Sep 3, 2026Price points (24h)11,753 pointsBiggest 24h dropBiggest 24h riseData updated Sep 5, 2026

What Do You Need to Run gpt-oss Locally? VRAM by Version

gpt-oss currently has 3 versions you can deploy locally. The smallest, gpt-oss 20B, needs 4GB of VRAM at Q4; the largest, gpt-oss 120B, needs 4GB. The cheapest device that gets one running is the GeForce RTX 4080, with no used-price data yet.

VRAM needed for each gpt-oss version

3 versions
VersionReleasedContext
gpt-oss 20BMoE20.9B (3.6B active)Aug 4, 2025128K4plus 12 GB of RAMGeForce RTX 4080 · 16 GB6,448,506
gpt-oss Safeguard 20BMoE20.9B (3.6B active)Sep 18, 2025128K4plus 12 GB of RAMGeForce RTX 4080 · 16 GB78,266
gpt-oss 120BMoE116.8B (5.1B active)Aug 4, 2025128K4plus 65 GB of RAMRTX PRO 5000 Blackwell 72GB · 72 GB5,259,501

Minimum VRAM = Q4_K_M weights + KV cache for an 8K context + 1GB runtime overhead, rounded up. The cheapest device is the first one that fits when sorting by median used price on the current price basis.

About gpt-oss

gpt-oss is published by OpenAI under Apache-2.0. This page covers 3 versions ranging from 20.9B to 116.8B parameters; structure parameters and quantized sizes are synced weekly from Hugging Face.

VendorOpenAI
LicenseApache-2.0
Hugging Face orgopenai