Configurator

Build your setup, without overflowing

Pick your card, the memory to leave to the system, the model and the context size: we check that everything fits in video memory and estimate the speed.

Speeds at context 0 are measured. Anything depending on context or concurrency is an estimate: every formula is shown, nothing is written to the database.

Graphics card

21 models measuredReserved for the OS

display, browser, system

Model50,8 tok/s · 9,2 Go measured · 1 runContext window

tok

max 16 384

KV cache

Video memory of the RTX 4070 Ti

9,9 Go used of 11,0 Go usable (12 GB)

1,1 Go left to add a model or grow a context.

▮ model (measured)▨ KV cache□ Reserved for the OS

Phi-4Q4_K_M · 4 096 tok

VRAM: 9,9 Go; 9,2 Go + 0,7 Go KV
Alone: 47,3 tok/s; Estimated
Concurrent: —; add a 2nd model