LLM
How to deploy Qwen3-4B on a GPU cloud
A 4B language model for chat and instruction-following. Full specs, license and use cases.
Qwen3-4B size and hardware requirements
4.0B
Total parameters
Dense (no MoE)
Architecture
BF16
Published precision
9.0 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 7.5 GB | 9.0 GB | RTX 4070 Super | 1 | $0.110/hr |
| FP8 (quantized) | 3.7 GB | 4.5 GB | RTX 4070 Super | 1 | $0.110/hr |
| INT4 (quantized) | 1.9 GB | 2.2 GB | RTX 4070 Super | 1 | $0.110/hr |
How to run Qwen3-4B
Run Qwen3-4B with vLLM
From Qwen/Qwen3-4B's own deployment docs.
vllm serve Qwen/Qwen3-4B --enable-reasoning --reasoning-parser deepseek_r1Source: https://huggingface.co/Qwen/Qwen3-4B/raw/main/README.md
Run Qwen3-4B with Ollama
Verified against Ollama's own library listing.
ollama run qwen3:4bDeploy Qwen3-4B on Aquanode
Aquanode has no one-click deploy template for Qwen3-4B; 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