Can I Run GPT-OSS 20B on NVIDIA GeForce RTX 3080 (10GB)?

Written by Jakub Rusinowski · Last updated August 15, 2026

Not at MXFP4 — that needs 10.6 GB and the NVIDIA GeForce RTX 3080 (10GB) has 10 GB. Drop to Q2_K and it fits in 7.8 GB, with up to 32K of context.

The numbers

ModelGPT-OSS 20B
Parameters20B
QuantizationMXFP4
VRAM needed10.6 GB
NVIDIA GeForce RTX 3080 (10GB) VRAM10 GB
VerdictRuns at a lower quant
Fits atQ2_K (7.8 GB)
Max context32K

What to do next

Quantize to Q2_K. That is the cheapest fix — it costs some quality but no money.

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.

Running GPT-OSS 20B on this card:

NVIDIA GeForce RTX 3080 10GB
10 GB VRAM · 320 W board power
2026 prices are volatile — check the current listing.
Check price on Amazon

Won't fit — rent GPT-OSS 20B instead

GPT-OSS 20B needs ~11 GB but this GPU has 10 GB. Rent a RTX 4090 (24 GB)-class GPU by the hour instead of buying one:

Affiliate links — we may earn a commission if you sign up, at no extra cost to you.

RunPod $0.34/hr
Rent on RunPod →
Vast.ai $0.35/hr · typical low · varies
Rent on Vast.ai →

Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.

Other GPT-OSS sizes on the NVIDIA GeForce RTX 3080 (10GB)

GPT-OSS 20B on nearby hardware

All GPT-OSS sizes on the NVIDIA GeForce RTX 3080 (10GB) | VRAM calculator for GPT-OSS 20B | NVIDIA GeForce RTX 3080 (10GB) GPU page | Check your hardware