Skip to main content
Local LLM Guide

Model

GPT-OSS 20B

Start with a supported compressed build and short context. 16GB RAM estimate. Best use: Local reasoning, coding experiments, tool calling, and privacy-minded users with 16GB-plus memory and patience today.

21B total / 3.6B activeReasoning

Best use

Local reasoning, coding experiments, tool calling, and privacy-minded users with 16GB-plus memory and patience today.

Memory planning

16GB RAM estimate

Expected pace

Depends on your hardware, app, and conversation length

License

Apache 2.0; read the model’s terms before use

Who should use this model?

  • Local reasoning, coding experiments, tool calling, and privacy-minded users with 16GB-plus memory and patience today.

Choose something else when

  • Avoid if your machine has under 16GB memory or you expect plug-and-play speed today locally.

What hardware makes sense?

The download is only part of the memory needed. Leave room for the app, the input it processes, and other open programs. For chat models, context includes the instructions, conversation, and answer. Longer context needs more memory.

CPU only
Memory or response time may limit use. Try a smaller model first.
8GB system memory
Use a smaller model for this memory limit.
16GB system memory
A possible starting point with a compressed model and short conversation; check the exact file size.
32GB system memory
A possible starting point with a compressed model and short conversation; check the exact file size.
8GB GPU memory
Use a smaller model for this memory limit.
12GB GPU memory
Memory or response time may limit use. Try a smaller model first.
24GB GPU memory
A possible starting point with a compressed model and short conversation; check the exact file size.
Apple unified memory
A possible starting point with a compressed model and short conversation; check the exact file size.

Model facts that change the decision

Parameters
21B total / 3.6B active
Input
Text
Published context limit
131,072 tokens
Model format
safetensors · GGUF · Ollama · MLX
Suggested compression
Q4_K_M for first local attempts unless a cited runtime recommends a different default.
Typical Q4 file
11.67GB before runtime and context overhead
Languages
Unknown

First setup

Ollama

ollama run gpt-oss:20b

LM Studio: Check that your installed app supports the exact model format and task before downloading it.

llama.cpp

Use the cited GGUF repository (lmstudio-community/gpt-oss-20b-GGUF) with current llama.cpp-compatible tooling.

Conditions that change the answer

  • This is the realistic GPT-OSS model for local users, but it is still a large model.
  • Use a Harmony-compatible runtime such as Ollama, LM Studio, vLLM, Transformers chat templates, or another integration that handles GPT-OSS formatting correctly.
  • Tool use depends on the app or server exposing tools; the model alone does not provide web browsing, Python, or function execution.
  • Higher reasoning effort can improve difficult tasks but will usually slow responses.
  • Full chain-of-thought may be available for debugging, but user-facing products should show concise reasoning summaries instead.
  • LM Studio lists 12GB minimum system memory, but 16GB-plus VRAM or unified memory is the safer beginner recommendation.
  • The 128k context window is an upper limit; long prompts can be slow and memory-heavy.
  • Common Q4, Q5, and Q8 GGUF variants save little space because GPT-OSS MoE feed-forward weights are generally kept at MXFP4.
  • Commercial use: permitted, subject to OpenAI gpt-oss usage policy
  • GPT-OSS 20B is OpenAI’s smaller open-weight reasoning model for capable local chat, coding, and tool-style workflows. It fits high-end consumer machines, but beginners must use compatible apps and expect variable speed locally with 128k context.

Read the controlling license text →