Local LLM model page

GPT-OSS (20B)

OpenAI open-weight reasoning model. First open release from OpenAI. Strong general + coding capabilities. 3.4M downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
20B
Minimum RAM
16 GB
Model size
12 GB
Quantization
Q5_K_M

Can GPT-OSS (20B) run locally?

GPT-OSS (20B) is best suited for mainstream Macs and PCs with 16 GB RAM. LocalClaw recommends Q5_K_M as the default quantization, with at least 16 GB RAM.

Search term for LM Studio or compatible runtimes: gpt-oss-20b

Hugging Face repository: openai/gpt-oss-20b

chatcodereasoningpowergeneral

Strengths

  • First open-weight model from OpenAI
  • 3.4M downloads
  • Strong general + coding
  • 128K context

Limitations

  • OpenAI restrictive license
  • Only 20B — smaller than expected
  • Limited fine-tuning allowed

Best use cases

  • General AI assistant
  • Coding
  • Reasoning
  • Research comparison

Benchmarks

Speed: 5/10

Quality: 8/10

Coding: 8/10

Reasoning: 9/10

Technical details

Developer: OpenAI

License: OpenAI Open Weight License

Context window: 131,072 tokens

Architecture: Transformer (OpenAI architecture)

Released: 2026-01

Similar models

qwen3-14bphi4-14bmistral-small-24b