text model · Qwen3 · Windows
Can I run Qwen3 30B-A3B on Nvidia GeForce RTX 4090 (24GB)?
Yes. Qwen3 30B-A3B runs on Nvidia GeForce RTX 4090 (24GB) at Q4_K_M (~20.7 GB of ~23 GB usable).
Fits at Q4_K_M (~20.7 GB of ~23 GB usable) but with little headroom, close other apps.
- Q4_K_M needed
- ~20.7 GB
- Usable on device
- ~23 GB
- Device memory
- 24 GB
- Best quant
- Q4_K_M
Run it
Pick your tool. All three load the same Q4_K_M weights.
ollama run qwen3:30b-a3b llama-cli -hf unsloth/Qwen3-30B-A3B-GGUF:Q4_K_M lms get unsloth/Qwen3-30B-A3B-GGUF AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
- Parameters
- 30.5B (MoE, 3.3B active)
- Q4_K_M size
- 18.6 GB
- Q8_0 size
- 32.5 GB
- Context
- 32k
- Ollama tag
- qwen3:30b-a3b
- Memory
- 24 GB vram
- Usable for weights
- ~23 GB
- Best runtime
- vLLM (Linux) / Ollama (CUDA)
You could also run
Run Qwen3 30B-A3B on other hardware
FAQ
Can Nvidia GeForce RTX 4090 (24GB) run Qwen3 30B-A3B?
Yes. Qwen3 30B-A3B runs on Nvidia GeForce RTX 4090 (24GB) at Q4_K_M (~20.7 GB of ~23 GB usable).
How much memory does Qwen3 30B-A3B need?
It is a tight fit on Nvidia GeForce RTX 4090 (24GB). At Q4_K_M the weights are ~18.6 GB; with KV cache and runtime overhead, budget ~20.7 GB at a 4k context. It is a Mixture-of-Experts model (30.5B total / 3.3B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run Qwen3 30B-A3B 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.
Sources
Memory figures are estimates. See methodology.