Hunyuan Instruct models

2 Hunyuan Instruct models from Tencent on Hugging Face, from 7.5B to 80.4B parameters, published by Tencent in BF16, with a 32K-token context. The smallest official model, Hunyuan-7B-Instruct, needs about 16.8 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.

Part of the Hunyuan series · Next generation: Hy3

Pick a size

One row per official Hunyuan Instruct size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
Hunyuan-7B-Instruct7.5B16.8 GB8.4 GB4.2 GBRTX A5000$0.176/hr4.0 GB
Hunyuan-A13B-Instruct80.4B180 GB89.8 GB44.9 GBAMD MI300X$2.63/hr4.0 GB

VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.

Official models (2)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Hunyuan-7B-Instruct7.5BBF1616.8 GBRTX A5000$0.176/hr
Hunyuan-A13B-Instruct80.4BBF16180 GBAMD MI300X$2.63/hr

VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.

More from Tencent

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.