DeepSeek V2 models

5 DeepSeek V2 models from DeepSeek on Hugging Face, from 15.7B to 235.7B parameters, published by DeepSeek in BF16, with a 160K-token context. The smallest official model, DeepSeek-V2-Lite, needs about 35.1 GB of VRAM at its published precision; the cheapest live fit is RTX A6000 at $0.363/hr.

Part of the DeepSeek series · Next generation: DeepSeek V3

Pick a size

One row per official DeepSeek V2 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-V2-Lite-Chat15.7B35.1 GB17.6 GB8.8 GBRTX A6000$0.363/hr0.95 GB
DeepSeek-V2235.7B527 GB263 GB132 GBAMD MI300X × 3$7.89/hr2.1 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 (4)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
DeepSeek-V2-Lite15.7BBF1635.1 GBRTX A6000$0.363/hr
DeepSeek-V2-Lite-Chat15.7BBF1635.1 GBRTX A6000$0.363/hr
DeepSeek-V2235.7BBF16527 GBAMD MI300X × 3$7.89/hr
DeepSeek-V2-Chat235.7BBF16527 GBAMD MI300X × 3$7.89/hr

Quantized versions (1)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
DeepSeek-V2.5-1210-FP8235.7BF8_E4M3263 GBRTX PRO 6000 × 3$4.13/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.