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

Qwen3-Coder-Next

by Qwen

79.7B params · text-generation · 1.1k likes · 1.2M downloads

Qwen3-Coder-Next is a 79.7B parameter model. At Q4 quantization it requires 40GB of VRAM. It runs comfortably on A100 PCIe 80 GB (30 tok/s), H100 SXM5 80 GB (60 tok/s), H200 SXM 141 GB (88 tok/s).

Inference providers

Provider$/1M in$/1M outThroughput
Novita146 tok/s

GPU compatibility

GPUVRAMQ4 DecodeVerdict
M4 Max 128GB128GB6 tok/stight
M4 Pro 48GB48GB3 tok/stight
A100 PCIe 80 GB80GB30 tok/scomfortable
H100 SXM5 80 GB80GB60 tok/scomfortable
M4 Max 64GB64GB6 tok/stight
H200 SXM 141 GB141GB88 tok/scomfortable
M2 Ultra 192GB192GB8 tok/stight
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0