LLM
How to deploy DeepSeek-V3.1 on a GPU cloud
A 685B (MoE) language model for chat and instruction-following. Full specs, license and use cases.
DeepSeek-V3.1 size and hardware requirements
684.5B
Total parameters
Mixture-of-experts: 8 of 256 experts active per token (exact active-parameter count not stated on the model card)
Active parameters
F8_E4M3
Published precision
765.0 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP8 (native) | 637.5 GB | 765.0 GB | RTX PRO 6000 | 8 | $13.12/hr |
| INT4 (quantized) | 318.8 GB | 382.5 GB | RTX A6000 | 8 | $2.64/hr |
How to run DeepSeek-V3.1
Run DeepSeek-V3.1 with vLLM
Generic example, not from the model's own docs: adjust flags (quantization, context length, parallelism) for your setup.
vllm serve deepseek-ai/DeepSeek-V3.1 --tensor-parallel-size 8Run DeepSeek-V3.1 with Ollama
Verified against Ollama's own library listing.
ollama run deepseek-v3.1Run DeepSeek-V3.1 with GGUF quantizations
Prebuilt GGUF weights published at unsloth/DeepSeek-V3.1-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf unsloth/DeepSeek-V3.1-GGUFDeploy DeepSeek-V3.1 on Aquanode
Aquanode has no one-click deploy template for DeepSeek-V3.1; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (8× RTX PRO 6000 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU pod