Recipes · 11 configurations

Machines ready to copy

For every budget, a model, the hardware, the engine and the command to run. Memory, speed and price use the same formulas as the rest of the site: estimates, not measurements.

All11 Budget3 Enthusiast1 Compact4 Pro1 Team1 Datacenter1

Enthusiast€3,500

A 32B model on a single card

The RTX 5090’s 32 GB fit a 32B in Q4 with a long context, and its bandwidth makes it very responsive.

Model Qwen3 32BHardware RTX 5090 32 GBPrecision Q4_K_MEngine llama.cppContext 32k

Memory29 / 32 GB

Estimated speed~50 tok/s

Power575 W

Memory use91 %

llama-server -hf unsloth/Qwen3-32B-GGUF:Q4_K_M -ngl 99 -c 32768

Load in the configurator The model The hardware