Tongyi-MAI models

2 Tongyi-MAI models from Tongyi-MAI on Hugging Face, from 6.2B to 6.2B parameters, published by Tongyi-MAI in BF16 and F32. The smallest official model, Z-Image, needs about 13.8 GB of VRAM at its published precision; the cheapest live fit is RTX 5060 Ti at $0.145/hr.

Pick a size

One row per official Tongyi-MAI 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
Z-Image-Turbo6.2B27.5 GB6.9 GB3.4 GBV100$0.220/hrnot published for this architecture

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
Z-Image6.2BBF1613.8 GBRTX 5060 Ti$0.145/hr
Z-Image-Turbo6.2BF3227.5 GBV100$0.220/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.

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

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