Meta: Llama 3.1 8B Instruct

Made by meta-llama. Open weights

Input price
$0.05
per 1M tokens
Output price
$0.08
per 1M tokens
Context window
131K
tokens
Quality
1,186
#324 on LMArena
Size
8.0B
parameters
Downloads
6.2M
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 47 tokens/s
  • NVIDIA GeForce RTX 306012 GBRuns44 to 62 tokens/s
  • NVIDIA GeForce RTX 4060 Ti 16 GB16 GBRuns35 to 50 tokens/s
  • NVIDIA GeForce RTX 409024 GBRuns123 to 175 tokens/s
  • NVIDIA GeForce RTX 509032 GBRuns219 to 310 tokens/s
  • Apple M1 Pro 32 GB32 GBRuns24 to 35 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