other
20.9B parameters
Commercial OK
Reviewed July 2026

GPT-OSS 20B

GPT-OSS 20B is OpenAI's open-weight 20.9B MoE, released August 2025 under Apache-2.0 and shipped natively in MXFP4 at 14GB. It is widely cited as the strongest general pick that fits a 16GB card, and sits at 11M Ollama pulls (#17 in the library).

License: Apache-2.0·Context: 131,072 tokens

Overview

GPT-OSS 20B is OpenAI's open-weight 20.9B MoE, released August 2025 under Apache-2.0 and shipped natively in MXFP4 at 14GB. It is widely cited as the strongest general pick that fits a 16GB card, and sits at 11M Ollama pulls (#17 in the library).

Strengths

  • Widely cited as the best general model that fits on 16GB cards
  • MoE design gives 20B-class quality at faster-than-dense decode speeds
  • Native MXFP4 release — no third-party quantization step

Weaknesses

  • 14GB weights leave little headroom on 16GB cards at longer context
  • Text-only — no vision or audio input
  • No smaller official quant; 14GB is the floor

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
MXFP414.0 GB16 GB

Get the model

Ollama

One-line install

ollama run gpt-oss:20bRead our Ollama review →

Hardware that runs this

Cards with enough VRAM for at least one quantization of GPT-OSS 20B.

NVIDIA GB200 NVL72
13824GB · nvidia
AMD Instinct MI350X
288GB · amd
NVIDIA B300 (Blackwell Ultra)
288GB · nvidia
AMD Instinct MI355X
288GB · amd
AMD Instinct MI325X
256GB · amd
AMD Instinct MI300X
192GB · amd
NVIDIA B200
192GB · nvidia
NVIDIA H100 NVL
188GB · nvidia
Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Step up
More capable — bigger memory footprint
Step down
Smaller — faster, runs on weaker hardware

Frequently asked

What's the minimum VRAM to run GPT-OSS 20B?

16GB of VRAM is enough to run GPT-OSS 20B at the MXFP4 quantization (file size 14.0 GB). Higher-quality quantizations need more.

Can I use GPT-OSS 20B commercially?

Yes — GPT-OSS 20B ships under the Apache-2.0, which permits commercial use. Always read the license text before deployment.

What's the context length of GPT-OSS 20B?

GPT-OSS 20B supports a context window of 131,072 tokens (about 131K).

How do I install GPT-OSS 20B with Ollama?

Run `ollama pull gpt-oss:20b` to download, then `ollama run gpt-oss:20b` to start a chat session. The default quantization is Q4_K_M.

Source: Vendor official documentation

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.

Related — keep moving

Compare hardware
Buyer guides
When it doesn't work
Recommended hardware
Before you buy

Verify GPT-OSS 20B runs on your specific hardware before committing money.

Will it run on my hardware? →Custom hardware comparison →GPU recommender (4 questions) →