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.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| deepseek-moe-16b-chat | 16.4B | 36.6 GB | 18.3 GB | 9.2 GB | RTX A6000 | $0.363/hr | 7.0 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)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| deepseek-moe-16b-base | 16.4B | BF16 | 36.6 GB | RTX A6000 | $0.363/hr |
| deepseek-moe-16b-chat | 16.4B | BF16 | 36.6 GB | RTX 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
- DeepSeek R1 (14 models)
- DeepSeek V3 (7 models)
- DeepSeek OCR (2 models)
- DeepSeek Coder (6 models)
- DeepSeek V2 (5 models)
- DeepSeek VL (3 models)
- DeepSeek V4 (3 models)