Coding
How to deploy Qwen3-Coder-480B-A35B-Instruct on a GPU cloud
A 480B (MoE) model tuned for code generation. Full specs, license and use cases.
Qwen3-Coder-480B-A35B-Instruct size and hardware requirements
480.2B
Total parameters
~35B active per token (mixture-of-experts; see total parameters above)
Active parameters
BF16
Published precision
1073.2 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 894.4 GB | 1073.2 GB | No capable live offer found | – | – |
| FP8 (quantized) | 447.2 GB | 536.6 GB | RTX PRO 6000 | 6 | $9.84/hr |
| INT4 (quantized) | 223.6 GB | 268.3 GB | RTX A6000 | 6 | $1.98/hr |
How to run Qwen3-Coder-480B-A35B-Instruct
Run Qwen3-Coder-480B-A35B-Instruct with vLLM
Generic example, not from the model's own docs: adjust flags (quantization, context length, parallelism) for your setup.
vllm serve Qwen/Qwen3-Coder-480B-A35B-Instruct --tensor-parallel-size 1Run Qwen3-Coder-480B-A35B-Instruct with Ollama
Verified against Ollama's own library listing.
ollama run qwen3-coder:480bRun Qwen3-Coder-480B-A35B-Instruct with GGUF quantizations
Prebuilt GGUF weights published at unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUFSource: https://huggingface.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF
Deploy Qwen3-Coder-480B-A35B-Instruct on Aquanode
Aquanode has no one-click deploy template for Qwen3-Coder-480B-A35B-Instruct; 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 (1073 GB VRAM or more).
- 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