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

DeepSeek-V3.2

by deepseek-ai

685B params · text-generation · 1.3k likes · 341.8k downloads

DeepSeek-V3.2 is a 685B parameter model. At Q4 quantization it requires 343GB of VRAM. It requires a GPU with at least 343GB of VRAM.

Inference providers

Provider$/1M in$/1M outThroughput
Novita29 tok/s
Fireworks81 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0