Qwen: Qwen3 32B

Made by qwen. Open weights

Input price
$0.08
per 1M tokens
Output price
$0.28
per 1M tokens
Context window
131K
tokens
Quality
1,340
#209 on LMArena
Size
33B
parameters
Downloads
3.7M
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 slowly2.5 to 3.5 tokens/s
  • NVIDIA GeForce RTX 306012 GBRuns, but slowly3.2 to 4.6 tokens/s
  • NVIDIA GeForce RTX 4060 Ti 16 GB16 GBRuns, but slowly4.3 to 6.1 tokens/s
  • NVIDIA GeForce RTX 409024 GBRuns30 to 43 tokens/s
  • NVIDIA GeForce RTX 509032 GBRuns54 to 76 tokens/s
  • Apple M1 Pro 32 GB32 GBRuns6.0 to 8.5 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