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

Llama-3.1-405B

by meta-llama

406B params · text-generation · 977 likes · 299.9k downloads

Llama-3.1-405B is a 406B parameter model. At Q4 quantization it requires 203GB of VRAM. It requires a GPU with at least 203GB of VRAM.

Inference providers

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