Skip to main content

VRAM Calculator

Can my GPU run this model?

Pick a model and quantization. See exactly how much VRAM it needs. Check GPU compatibility instantly.

Step 1

Pick a model

Search by name, or scroll the list. Custom param count at the bottom of the panel.

Step 2

Quantization

Recommended for models 14B and above. Best balance of size and quality.

Step 3

Context length

32Ktokensmax 1M

Pick a model or enter a parameter count to see the VRAM estimate.

Every model on this page runs in Bodega One.

Pick a model, connect a provider, start coding. No config files. One-time purchase.

Join the Waitlist

Estimates based on published model architectures and quantization specifications. Actual usage may vary by 1-2 GB depending on runtime, driver version, and system configuration. KV cache calculated at FP16. VRAM figures do not include memory used by other applications. Last verified March 2026.