Qwen: Qwen3 8B

Made by qwen. Open weights

Input price
$0.117
per 1M tokens
Output price
$0.455
per 1M tokens
Context window
131K
tokens
Quality
—
LMArena score
Size
8.2B
parameters
Downloads
10.1M
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 GBRuns33 to 46 tokens/s
  • NVIDIA GeForce RTX 306012 GBRuns43 to 61 tokens/s
  • NVIDIA GeForce RTX 4060 Ti 16 GB16 GBRuns34 to 49 tokens/s
  • NVIDIA GeForce RTX 409024 GBRuns121 to 171 tokens/s
  • NVIDIA GeForce RTX 509032 GBRuns214 to 304 tokens/s
  • Apple M1 Pro 32 GB32 GBRuns24 to 34 tokens/s
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