Device profile · Windows

Best local LLMs for Nvidia GeForce RTX 5090 (32GB)

Nvidia GeForce RTX 5090 (32GB) has ~31 GB estimated usable for weights, cache and runtime; 129 of 161 tracked models fit at the estimated 4K baseline. Best tool: LM Studio.

127 fit with room 2 tight fit 32 too heavy

Usable memory: ~31 GB
Estimated fits: 129
Too large: 32
Suggested fit: 30.5B

Suggested fit Q4_K_M

Qwen3 30B-A3B Yes

Runs at Q4_K_M using ~20.7 GB of ~31 GB usable.

The suggested model uses recorded Arena scores where available, then estimated fit and speed. Score coverage is partial; it does not establish the best model for every task. Fit is an estimate, not a benchmark on this device.

Set up Qwen3 30B-A3B on this device →

Estimated memory fits on Nvidia GeForce RTX 5090 (32GB)

Compatible models 129 total

Best way to run models on Windows

Runtime guide Windows

Beginner: LM Studio, Best GUI on Windows, auto-detects CUDA/Vulkan backends.

Power user: Ollama (CUDA), Scriptable server; CUDA path is fastest on NVIDIA.

AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.

Full Windows tool guide →

FAQ

What is the best local LLM for Nvidia GeForce RTX 5090 (32GB)?

Qwen3 30B-A3B is a suggested fit, using ~20.7 GB at Q4_K_M of the ~31 GB usable on Nvidia GeForce RTX 5090 (32GB).

How much of Nvidia GeForce RTX 5090 (32GB)'s memory can I use for a model?

About 31 GB. On a discrete GPU, leave ~1 GB of VRAM for the driver and display.

Which tool should I use on Windows?

LM Studio (Best GUI on Windows, auto-detects CUDA/Vulkan backends.) or Ollama (CUDA) for speed. AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.