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

Qwen3-Coder-480B-A35B-Instruct

by Qwen

480B params · text-generation · 1.3k likes · 69.2k downloads

Qwen3-Coder-480B-A35B-Instruct is a 480B parameter model. At Q4 quantization it requires 240GB of VRAM. It requires a GPU with at least 240GB of VRAM.

Inference providers

Provider$/1M in$/1M outThroughput
Novita64 tok/s
Hyperbolic66 tok/s
Together AI58 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0