OpenAI: gpt-oss-120b

Made by openai. Open weights

Input price
$0.037
per 1M tokens
Output price
$0.17
per 1M tokens
Context window
131K
tokens
Quality
1,365
#189 on LMArena
Size
117B
parameters
Downloads
4.1M
on Hugging Face, last 30 days

Can I run it locally?

Estimate for the Q4_K_M version with an 8K context. Pick your own card and settings in the calculator.

  • NVIDIA GeForce RTX 40608 GBRuns, but slowly0.5 to 0.8 tokens/s
  • NVIDIA GeForce RTX 306012 GBRuns, but slowly0.6 to 0.8 tokens/s
  • NVIDIA GeForce RTX 4060 Ti 16 GB16 GBRuns, but slowly0.6 to 0.9 tokens/s
  • NVIDIA GeForce RTX 409024 GBRuns, but slowly0.7 to 1.0 tokens/s
  • NVIDIA GeForce RTX 509032 GBRuns, but slowly0.9 to 1.3 tokens/s
  • Apple M1 Pro 32 GB32 GBWill not run—
Check my computer

Prices: OpenRouter, refreshed 8 Oct 2026. Quality: LMArena (CC BY 4.0), leaderboard of 2 Oct 2026. Model page on Hugging Face