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

cogito-671b-v2.1-FP8

by deepcogito

671B params · text-generation · 11 likes · 251 downloads

cogito-671b-v2.1-FP8 is a 671B parameter model. At Q4 quantization it requires 336GB of VRAM. It requires a GPU with at least 336GB of VRAM.

Inference providers

Provider$/1M in$/1M outThroughput
Together AI77 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0