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

Qwen3.5-397B-A17B

by Qwen

403B params · image-text-to-text · 1.5k likes · 639.0k downloads

Qwen3.5-397B-A17B is a 403B parameter model. At Q4 quantization it requires 202GB of VRAM. It requires a GPU with at least 202GB of VRAM.

Inference providers

Provider$/1M in$/1M outThroughput
Novita73 tok/s
Together AI102 tok/s
Featherless
Scaleway105 tok/s
OVHcloud86 tok/s
deepinfra32 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0