Reasoning
How to deploy DeepSeek-R1-Distill-Qwen-1.5B on a GPU cloud
A 1.8B model tuned to reason step by step before answering. Full specs, license and use cases.
DeepSeek-R1-Distill-Qwen-1.5B size and hardware requirements
1.8B
Total parameters
Dense (no MoE)
Architecture
BF16
Published precision
4.0 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 3.3 GB | 4.0 GB | RTX 4070 Super | 1 | $0.110/hr |
| FP8 (quantized) | 1.7 GB | 2.0 GB | RTX 4070 Super | 1 | $0.110/hr |
| INT4 (quantized) | 0.8 GB | 1.0 GB | A16 | 1 | $0.059/hr |
How to run DeepSeek-R1-Distill-Qwen-1.5B
Run DeepSeek-R1-Distill-Qwen-1.5B with vLLM
From deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B's own deployment docs.
vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eagerSource: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/raw/main/README.md
Run DeepSeek-R1-Distill-Qwen-1.5B with GGUF quantizations
Prebuilt GGUF weights published at unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUFSource: https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF
Deploy DeepSeek-R1-Distill-Qwen-1.5B on Aquanode
Aquanode has no one-click deploy template for DeepSeek-R1-Distill-Qwen-1.5B; 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 (1× RTX 4070 Super 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