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

Hunyuan-A13B-Instruct

by tencent

80.4B params · text-generation · 616 likes · 16.5k downloads

Hunyuan-A13B-Instruct is a 80.4B parameter model. At Q4 quantization it requires 40GB of VRAM. It runs comfortably on H100 SXM5 80 GB (60 tok/s), H200 SXM 141 GB (87 tok/s).

GPU compatibility

GPUVRAMQ4 DecodeVerdict
M4 Max 128GB128GB5 tok/stight
M4 Pro 48GB48GB2 tok/stight
A100 PCIe 80 GB80GB29 tok/stight
H100 SXM5 80 GB80GB60 tok/scomfortable
M4 Max 64GB64GB5 tok/stight
H200 SXM 141 GB141GB87 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