VRAM Fit Calculator
Estimate whether a quantized language or vision model fits your GPU at the selected context size.
Open calculator →Free utilities
Use the VRAM calculator to estimate model memory needs, or browse the model catalog for a dated record of tested hosted endpoints.
Estimate whether a quantized language or vision model fits your GPU at the selected context size.
Open calculator →Filter the recorded model and provider checks. Availability can change after the catalog snapshot.
Browse catalog →