DeepSeek MoE models

2 DeepSeek MoE models from DeepSeek on Hugging Face, from 16.4B to 16.4B parameters, published by DeepSeek in BF16, with a 4K-token context. The smallest official model, deepseek-moe-16b-base, needs about 36.6 GB of VRAM at its published precision; the cheapest live fit is RTX A6000 at $0.363/hr.

Part of the DeepSeek series

Pick a size

One row per official DeepSeek MoE 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
deepseek-moe-16b-chat16.4B36.6 GB18.3 GB9.2 GBRTX A6000$0.363/hr7.0 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
deepseek-moe-16b-base16.4BBF1636.6 GBRTX A6000$0.363/hr
deepseek-moe-16b-chat16.4BBF1636.6 GBRTX A6000$0.363/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 DeepSeek

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

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