What GPU do I need to run Qwen/Qwen3-Coder-480B-A35B-Instruct?
A 480B (MoE) model tuned for code generation. 480.2B parameters, published in BF16. View on Hugging Face
Qwen3-Coder-480B-A35B-Instruct is published by Qwen on Hugging Face, with 31,122 downloads and 1,366 likes to date. It's a Qwen3MoeForCausalLM model built for text-generation, published natively in BF16.
What Qwen3-Coder-480B-A35B-Instruct is
Qwen3-Coder-480B-A35B-Instruct is a 480B-parameter mixture-of-experts language model published by Alibaba (Qwen) on Hugging Face. It is tuned specifically for code generation and completion. It is released under Apache 2.0.
License note: fully permissive, no gating and no usage restrictions. Facts in this section are sourced from Qwen3-Coder-480B-A35B-Instruct's Hugging Face model card, not benchmarked by Aquanode.
What it's used for
- Code generation and completion
- Code review / refactoring assistants
- IDE copilots
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 894.4 GB | 1073.2 GB | AMD MI300X | 6 | $15.77/hr |
| FP8 (quantized) | 447.2 GB | 536.6 GB | AMD MI300X | 3 | $7.89/hr |
| INT4 (quantized) | 223.6 GB | 268.3 GB | RTX A6000 | 6 | $2.18/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Qwen3-Coder-480B-A35B-Instruct at its published (BF16) precision: 6× AMD MI300X, at $2.63/hr per GPU ($15.77/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Qwen3-Coder-480B-A35B-Instruct: KV cache by context length
The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.
Grouped-query attention: every layer caches keys and values for a few shared KV heads. Cached per token: 253,952 bytes at 16-bit.
| Context | KV cache, one sequence |
|---|---|
| 4K | 0.97 GB |
| 32K | 7.8 GB |
| 128K | 31.0 GB |
| 256K (model maximum) | 62.0 GB |
Computed from the layer, head and window counts in the model's own configuration (Qwen/Qwen3-Coder-480B-A35B-Instruct), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.
Qwen3-Coder-480B-A35B-Instruct: common questions
Can Qwen3-Coder-480B-A35B-Instruct run on a single GPU?
No. At BF16 it needs 1073.2 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 192.0 GB AMD MI300X, and it takes 6 of them.
How many GPUs do I need to run Qwen3-Coder-480B-A35B-Instruct?
6 at BF16. It needs 1073.2 GB of VRAM and the cheapest capable live offer is a 192.0 GB AMD MI300X, so 6 of them come to $15.77/hr in total.
Does quantizing Qwen3-Coder-480B-A35B-Instruct lower the GPU bill?
Yes. At BF16 the cheapest live fit is 6 AMD MI300X cards at $15.77/hr. At INT4 (quantized) it drops to 6 RTX A6000 cards at $2.18/hr, provided a quantized checkpoint exists for it.
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 6Run 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 (6× AMD MI300X 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 podWeight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Qwen3 models
- Qwen3-Coder-480B-A35B-Instruct-FP8 (480.2B, F8_E4M3)
- Qwen3-235B-A22B-Instruct-2507-FP8 (235.1B, F8_E4M3)
- Qwen3-235B-A22B-Thinking-2507-FP8 (235.1B, F8_E4M3)
- Qwen3-235B-A22B-FP8 (235.1B, F8_E4M3)
- Qwen3-235B-A22B (235.1B, BF16)
Alternatives at this size
Other models for text-generation within about a third of Qwen3-Coder-480B-A35B-Instruct's 480.2B parameters, from other model lines.
- DeepSeek-R1 (684.5B, F8_E4M3)
- NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 (560.5B, BF16)
- Ornith-1.5-397B (403.4B, BF16)
- Llama-3.1-405B (405.9B, BF16)
- A.X-K2 (691.7B, F8_E4M3)
More on Qwen3-Coder-480B-A35B-Instruct
Fits on a 288 GB GPU at INT4: every model that fits in 288 GB.
Best coding models: how Qwen3-Coder-480B-A35B-Instruct ranks against the rest.
Related reading: AMD MI300X pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.
