Microsoft: Phi 4

Made by microsoft. Open weights

Input price
$0.07
per 1M tokens
Output price
$0.14
per 1M tokens
Context window
16K
tokens
Quality
1,217
#311 on LMArena
Size
15B
parameters
Downloads
389.8K
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 slowly9.2 to 13 tokens/s
  • NVIDIA GeForce RTX 306012 GBRuns24 to 34 tokens/s
  • NVIDIA GeForce RTX 4060 Ti 16 GB16 GBRuns19 to 27 tokens/s
  • NVIDIA GeForce RTX 409024 GBRuns67 to 95 tokens/s
  • NVIDIA GeForce RTX 509032 GBRuns120 to 170 tokens/s
  • Apple M1 Pro 32 GB32 GBRuns13 to 19 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