text model · Qwen3-Coder · Windows
Can I run Qwen3-Coder 480B-A35B Instruct on Nvidia GeForce RTX 3060 (12GB)?
No. Qwen3-Coder 480B-A35B Instruct needs ~276.2 GB even at Q4_K_M, but Nvidia GeForce RTX 3060 (12GB) only has ~11 GB usable.
Needs ~276.2 GB even at Q4_K_M, but only ~11 GB is usable.
That figure is at a 4k context and moves about ±15% as context length changes.
The gap is about 265.2 GB: Qwen3-Coder 480B-A35B Instruct needs roughly 276.2 GB at Q4_K_M and Nvidia GeForce RTX 3060 (12GB) leaves only about 11 GB usable for a model. No single tracked device has enough memory; Qwen3-Coder 480B-A35B Instruct needs a multi-GPU or high-memory rig.
- Q4_K_M needed
- ~276.2 GB
- Usable on device
- ~11 GB
- Device memory
- 12 GB
Which quant fits
- Parameters
- 480B (MoE, 35B active)
- Q4_K_M size
- 270.14 GB
- Q8_0 size
- 475.3 GB
- Context
- 256k
- Ollama tag
- qwen3-coder:480b
- Memory
- 12 GB vram
- Usable for weights
- ~11 GB
- Power draw
- ~170 W
- Best runtime
- Ollama (CUDA) / llama.cpp CUDA
What you can run instead
FAQ
Can Nvidia GeForce RTX 3060 (12GB) run Qwen3-Coder 480B-A35B Instruct?
No. Qwen3-Coder 480B-A35B Instruct needs ~276.2 GB even at Q4_K_M, but Nvidia GeForce RTX 3060 (12GB) only has ~11 GB usable.
How much memory does Qwen3-Coder 480B-A35B Instruct need?
Nvidia GeForce RTX 3060 (12GB) does not have enough memory. At Q4_K_M the weights are ~270.14 GB; with KV cache and runtime overhead, budget ~276.2 GB at a 4k context. It is a Mixture-of-Experts model (480B total / 35B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run Qwen3-Coder 480B-A35B Instruct on Windows?
LM Studio for a simple setup; Ollama (CUDA) for the most speed. AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/qwen3-coder-480b/nvidia-rtx-3060-12gb) Sources
Weights are measured from GGUF files; KV cache and overhead are computed, so totals can vary ~15% with context and runtime. Any tok/s is a bandwidth estimate. See methodology.