OpenAI makes the GPT OSS 20B, an open-weight chat model that takes in and outputs text. It is designed for agentic tasks like function calling, web search, code execution, and structured output, with configurable reasoning effort.
Input
Output
Context
131K
Max Output
131K
Parameters
20.9B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
Measured speed: 141 tok/s output speed · 14.6 s to first answer token · 0.39 s to first token
Bands compare this model with every model the same suite measured in our catalog.
Download 13.8 GB · Runs on vLLM v0.32.0 · 100 GGUF builds
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 39.0 GB | 45.6 GB | 1x Biren BR100 (64 GB) |
| INT8 | 19.5 GB | 25.1 GB | 1x Tenstorrent Blackhole p150 (32 GB) |
| INT4 | 9.74 GB | 14.9 GB | 1x NVIDIA GeForce RTX 3090 (24 GB) |
Computed by Inferbase from the 20,914,757,184 parameters in the creator's Hugging Face repository; one request adds its KV cache, activations and framework overhead, with the layer layout estimated from the parameter count.
Specification sources
As of Nov 10, 2026.
Answered from the facts on this page, with their sources.
GPT OSS 20B has a context window of 131,072 tokens and a maximum output of 131,072 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. GPT OSS 20B is an open-weight model under the Apache 2.0 license. You can download and self-host it within the license terms.
GPT OSS 20B has 20,914,757,184 parameters (20.9B), as stated in the creator's Hugging Face repository.
Strengths: Open weights under a permissive license (apache-2.0); 131K token context window; In the top 25% on competition math (AIME 2025) among measured models. Limitations: Below average on long-context reasoning among measured models. Each is computed from the model's stated facts and benchmark results.
GPT OSS 20B accepts Text and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
GPT OSS 20B has published results from Artificial Analysis and Epoch AI. The Benchmarks card shows each score as reported, with its band among the models the same source measured. Scores are never combined across sources.
Yes. GPT OSS 20B is available on Inferbase Managed through the OpenAI-compatible API as openai-gpt-oss-20b. Request it by name, or request auto and routing picks it when it fits the request best.
The weights take 39.0 GB at FP16 / BF16, 19.5 GB at INT8, 9.7 GB at INT4, computed from the 20,914,757,184 parameters its creator publishes. Each request adds its KV cache and the framework's overhead. The hardware section shows one request and the smallest GPU that fits; the GPU planner sizes it for your context length and traffic.
Start on the free plan with 5,000 requests a month, no card required.