gpt-oss-20b

Find hardware that runs gpt-oss-20b on your budget

Parameters
21.51 B
Active per token
3.6 B
Architecture
MoE
Modality
text
Max context
131072
Released
2025-08-05
License
apache-2.0

Measurements

Decode is token generation — the speed you feel while an answer streams. Prefill is prompt processing — the wait before it starts. Why bandwidth predicts decode speed.

What verified, single-source and estimated mean, and the same rows with every filter and sort in the benchmarks explorer.

Speed over time

Cheapest hardware by target speed

The lowest-priced entry that reaches each threshold, using the strongest evidence available. Estimated rows are marked.