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

NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

by nvidia

335B params · text-generation · 202 likes · 331.3k downloads

NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 is a 335B parameter model. At Q4 quantization it requires 168GB of VRAM. It requires a GPU with at least 168GB of VRAM.

Inference providers

Provider$/1M in$/1M outThroughput
Together AI149 tok/s
Fireworks138 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0