gpt-oss-20b VRAM and RAM requirements

OpenAI's smaller open-weight MoE. Weights are 20.9B; active parameters are a few billion.

Total weights

20.9B

Active

3.6B

Context

131K tokens

License

Apache-2.0

openai/gpt-oss-20b on Hugging Face · 5,956,790 downloads on the Hub snapshot in this catalog

Memory

• Q4

  11.8 GB

• Q8

  12.3 GB

• FP16

  50.2 GB

• GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.
• Formula estimate: parameter count × bytes per weight × 1.20. No GGUF file size is stored for this quant.

Compatible hardware

44 of 64 machines fit at Q4 or better. Fits means the estimate is inside the usable memory. Tight means less than 2 GB of room.

Amazon links are affiliate searches, not live prices.