Hy3 models

3 Hy3 models from Tencent on Hugging Face, from 298.8B to 298.8B parameters, published by Tencent in BF16, with a 256K-token context. The smallest official model, Hy3, needs about 668 GB of VRAM at its published precision; the cheapest live fit is AMD MI300X at $10.52/hr.

Part of the Hunyuan series · Previous generation: Hunyuan Instruct · Next generation: Hy4

Pick a size

One row per official Hy3 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
Hy3-preview298.8B668 GB334 GB167 GBAMD MI300X × 4$10.52/hr10.0 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
Hy3298.8BBF16668 GBAMD MI300X × 4$10.52/hr
Hy3-preview298.8BBF16668 GBAMD MI300X × 4$10.52/hr

Quantized versions (1)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Hy3-FP8298.8BF8_E4M3334 GBAMD MI300X × 2$5.26/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.