Gpt Oss 20B
OpenAI's Gpt Oss 20B is a chat model designed for powerful reasoning, agentic tasks, and versatile developer use cases, with a notable technical trait of having a large context window of 131,072 tokens. It is genuinely best at handling math-related tasks, as evidenced by its top 25% score on the Math Index.
Input
Output
Context
131K
Max Output
131K
Parameters
21.5B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output Tokens131,072 tokens
Parameters21.5B
Release DateAug 4, 2025
Training CutoffJun 1, 2024
Licenseapache-2.0
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
9.8%
HLE
68.8%
GPQA
34.4%
SciCode
74.8%
MMLU Pro
89.3
Math
18.5
Coding
77.7%
LiveCodeBench
14.9
Intelligence
225
Speed (tok/s)
9.3
TTFA (s)
0.443
TTFT (s)
Resources & Links
Estimated GPU Requirements for Gpt Oss 20B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.