GPT-OSS 20B — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated August 15, 2026

Model library → GPT-OSS → GPT-OSS 20B

The size of the gpt-oss pair most people actually run. Shipped in MXFP4 precision — the MoE weights are quantized to ~4.25 bits per parameter — so it loads in roughly 14 GB and runs comfortably on a 16GB card, far below what a 20B parameter count would normally imply. Ollama supports MXFP4 natively, with no extra conversion step. 128K context, Apache 2.0, and o3-mini-class reasoning.

GPT-OSS 20B needs about 13 GB of VRAM at MXFP4 — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters20 Billion
Context window128,000
ArchitectureMixture-of-Experts (MXFP4)
ProviderOpenAI
LicenceApache 2.0
Specified atMXFP4
System RAM32 GB
Record updated2026-08-15

Licence

Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), at 8K context. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K6.9 GB8.1 GB~245 tok/s (est.)Fits comfortably
Q3_K_M8.9 GB10.1 GB~220 tok/s (est.)Fits comfortably
Q4_K_M12.6 GB13.8 GB~186 tok/s (est.)Fits comfortably
Q5_K_M14.8 GB16.0 GB~170 tok/s (est.)Fits comfortably
Q6_K17.1 GB18.3 GB~156 tok/s (est.)Fits comfortably
Q8_022.2 GB23.4 GB~132 tok/s (est.)Tight fit
F1641.8 GB43.0 GB~12 tok/s (est.)Offloads to system RAM (slow)

Want the memory numbers alone, at every quantization level and your own context length? Use the GPT-OSS 20B VRAM calculator.

Buy This HardwareAMD Radeon RX 9060 XT 16GB — 16 GB VRAM · 160 W board powerDeploy in the Cloud NowRTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Recommended GPU

The cheapest catalogued GPU that runs GPT-OSS 20B is the AMD Radeon RX 9060 XT 16GB (16 GB).

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.
AMD Radeon RX 9060 XT 16GB
16 GB VRAM · 160 W board power
2026 prices are volatile — check the current listing.
Check price on Amazon

How to Run GPT-OSS 20B

Install Ollama, then run:

ollama run gpt-oss:20b

Weights on Hugging Face: openai/gpt-oss-20b.

Best for: reasoning, general purpose, local first, privacy sensitive.

Can I Run GPT-OSS 20B on My GPU?

Other GPT-OSS Sizes

GPT-OSS 20B — Frequently Asked Questions

How much VRAM does GPT-OSS 20B need?
About 13 GB at MXFP4 — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does GPT-OSS 20B run on an RTX 4090 (24 GB)?
Yes. GPT-OSS 20B needs about 13 GB at MXFP4, inside a 24 GB card, at an estimated 186 tokens/sec.
How do I run GPT-OSS 20B locally?
Install Ollama and run `ollama run gpt-oss:20b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does GPT-OSS come in?
GPT-oss 120B (71 GB), GPT-OSS 20B (13 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All GPT-OSS models | VRAM calculator | Check your own hardware