DeepSeek V3 models
7 DeepSeek V3 models from DeepSeek on Hugging Face, from 684.5B to 685.4B parameters, published by DeepSeek in F8_E4M3, with a 160K-token context. The smallest official model, DeepSeek-V3, needs about 765 GB of VRAM at its published precision.
Part of the DeepSeek series · Previous generation: DeepSeek V2 · Next generation: DeepSeek V4
Pick a size
One row per official DeepSeek V3 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-V3-0324 | 684.5B | 765 GB | – | 383 GB | No live fit | – | 2.1 GB |
| DeepSeek-V3.2 | 685.4B | 766 GB | – | 383 GB | No live fit | – | 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 (7)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| DeepSeek-V3 | 684.5B | F8_E4M3 | 765 GB | No live fit | – |
| DeepSeek-V3-0324 | 684.5B | F8_E4M3 | 765 GB | No live fit | – |
| DeepSeek-V3.1 | 684.5B | F8_E4M3 | 765 GB | No live fit | – |
| DeepSeek-V3.1-Base | 684.5B | F8_E4M3 | 765 GB | No live fit | – |
| DeepSeek-V3.1-Terminus | 684.5B | F8_E4M3 | 765 GB | No live fit | – |
| DeepSeek-V3.2 | 685.4B | F8_E4M3 | 766 GB | No live fit | – |
| DeepSeek-V3.2-Exp | 685.4B | F8_E4M3 | 766 GB | No live fit | – |
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 OCR (2 models)
- DeepSeek Coder (6 models)
- DeepSeek V2 (5 models)
- DeepSeek VL (3 models)
- DeepSeek MoE (2 models)
- DeepSeek V4 (3 models)
