Model reference · open weights

ideogram-instant

Image fal Text→image 1 build Non-commercial 0 dl/mo

ideogram-instant is an open-weight image model from fal. ideogram-v4-instant (BF16) weighs 18.6 GB; the smallest configuration that runs it is RTX 5090 32 GB.

  • Ideogram 4 Instant is a text-to-image model developed by fal that generates images in eight denoising steps without runtime classifier-free guidance.
  • The model contains approximately 9.28 billion parameters and is released as BF16 weights captured before quantization-aware distillation.
  • It operates under the Ideogram 4 Non-Commercial Model Agreement.

Summary of the fal/ideogram-v4-instant model card, 2026-10-01

What it is

Released byfal
Released2026-07-13
Parameters9.3B
VRAM18.6 GB for the weights

What it runs on

Memory and cards for ideogram-v4-instant (BF16)

18.6 GBweights, file size
5.0 GBworking memory, one 1024² image
537 MBruntime overhead
CardOne imageMemory
RTX 3060 12 GB … RTX 4090 24 GBdoes not fit
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

How it works

How image models work

Text promptwhat to makeText encoderunderstands itDiffusion stepsdenoise to pixelsImagePNG / JPEGA diffusion model starts from noise and denoises it, guided by your prompt, into a finished image.

Running it yourself

Run it on a rented GPU

Rent a machine by the hour. How to run this model is on its model card.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms