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

Qwen3.5-122B-A10B

by Qwen

125B params · image-text-to-text · 418 likes · 314.8k downloads

Qwen3.5-122B-A10B is a 125B parameter model. At Q4 quantization it requires 63GB of VRAM. It runs comfortably on H100 SXM5 80 GB (38 tok/s), H200 SXM 141 GB (56 tok/s).

Inference providers

Provider$/1M in$/1M outThroughput
Novita74 tok/s

GPU compatibility

GPUVRAMQ4 DecodeVerdict
M4 Max 128GB128GB3 tok/stight
A100 PCIe 80 GB80GB19 tok/stight
H100 SXM5 80 GB80GB38 tok/scomfortable
H200 SXM 141 GB141GB56 tok/scomfortable
M2 Ultra 192GB192GB5 tok/stight
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0