Coding
How to deploy Qwen3-Coder-Next on a GPU cloud
A 79.7B (MoE) model tuned for code generation. Full specs, license and use cases.
Qwen3-Coder-Next size and hardware requirements
79.7B
Total parameters
Mixture-of-experts: 10 of 512 experts active per token (exact active-parameter count not stated on the model card)
Active parameters
BF16
Published precision
178.1 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 148.4 GB | 178.1 GB | RTX 3090 | 8 | $1.18/hr |
| FP8 (quantized) | 74.2 GB | 89.0 GB | RTX PRO 6000 | 1 | $1.64/hr |
| INT4 (quantized) | 37.1 GB | 44.5 GB | RTX A6000 | 1 | $0.330/hr |
How to run Qwen3-Coder-Next
Run Qwen3-Coder-Next with vLLM
From Qwen/Qwen3-Coder-Next's own deployment docs.
vllm serve Qwen/Qwen3-Coder-Next --port 8000 --tensor-parallel-size 2 --enable-auto-tool-choice --tool-call-parser qwen3_coderSource: https://huggingface.co/Qwen/Qwen3-Coder-Next/raw/main/README.md
Run Qwen3-Coder-Next with Ollama
Verified against Ollama's own library listing.
ollama run qwen3-coder-nextRun Qwen3-Coder-Next with GGUF quantizations
Prebuilt GGUF weights published at unsloth/Qwen3-Coder-Next-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf unsloth/Qwen3-Coder-Next-GGUFSource: https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF
Deploy Qwen3-Coder-Next on Aquanode
Aquanode has no one-click deploy template for Qwen3-Coder-Next; 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 3090 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