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.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| DeepSeek-V2-Lite-Chat | 15.7B | 35.1 GB | 17.6 GB | 8.8 GB | RTX A6000 | $0.363/hr | 0.95 GB |
| DeepSeek-V2 | 235.7B | 527 GB | 263 GB | 132 GB | AMD MI300X × 3 | $7.89/hr | 2.1 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)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| DeepSeek-V2-Lite | 15.7B | BF16 | 35.1 GB | RTX A6000 | $0.363/hr |
| DeepSeek-V2-Lite-Chat | 15.7B | BF16 | 35.1 GB | RTX A6000 | $0.363/hr |
| DeepSeek-V2 | 235.7B | BF16 | 527 GB | AMD MI300X × 3 | $7.89/hr |
| DeepSeek-V2-Chat | 235.7B | BF16 | 527 GB | AMD MI300X × 3 | $7.89/hr |
Quantized versions (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| DeepSeek-V2.5-1210-FP8 | 235.7B | F8_E4M3 | 263 GB | RTX 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
- DeepSeek R1 (14 models)
- DeepSeek V3 (7 models)
- DeepSeek OCR (2 models)
- DeepSeek Coder (6 models)
- DeepSeek VL (3 models)
- DeepSeek MoE (2 models)
- DeepSeek V4 (3 models)