vram.run Models Hardware Providers Cloud State of Inference
API provider data is live · Hardware & cloud pricing curated 2026-02-23

Kimi-K2-Instruct

by moonshotai

1026B params · text-generation · 2.3k likes · 94.8k downloads

Kimi-K2-Instruct is a 1026B parameter model. At Q4 quantization it requires 513GB of VRAM. It requires a GPU with at least 513GB of VRAM.

Inference providers

Provider$/1M in$/1M outThroughput
Novita42 tok/s
Featherless
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0