Ideogram 4
Frontierby Ideogram
Ideogram 4 is a 9.3B single-stream DiT text-to-image foundation model trained from scratch, with best-in-class in-image text rendering for signage, logos, and captions. Uses a 34-layer unified transformer over concatenated text and image tokens, with Qwen3-VL-8B as the text encoder. Supports any multiple-of-16 resolution up to 2048x2048.
VRAM requirements, GPU fit, and setup notes for Ideogram 4, including 8GB/12GB fit guidance where relevant. Recommended runtimes: ComfyUI and Diffusers support. Best download size: ~5.8 GB at Q4_K_M.
- Best-in-class in-image text rendering for logos, signage, and captions
- 9.3B single-stream DiT (34 layers) over unified text+image tokens
- Qwen3-VL-8B text encoder with hidden states from 13 intermediate layers
- Any multiple-of-16 resolution from 256 up to 2048 per side
Your hardware
Detecting...
Image Quality Benchmarks
Measured quality metrics for Ideogram 4 outputs.
How often humans prefer this model's output (0-100%)
Visual quality and composition rating (5-9 scale)
Text-image alignment accuracy (higher is better)
VRAM Requirements by Resolution and Precision
Compare which GPUs can run Ideogram 4 at different precisions. FP8 uses less memory than FP16 when available, and the grade shows how comfortably each GPU handles the workload.
FP16 (full precision)
| Resolution | VRAM Required | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 | 37.2 GB | F | F | F | F |
| 768×768 | 37.4 GB | F | F | F | F |
| 1024×1024 | 37.7 GB | F | F | F | F |
FP8 (~40% less VRAM)
| Resolution | VRAM Required | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 | 19.0 GB | S | F | F | B |
| 768×768 | 19.2 GB | A | F | F | B |
| 1024×1024 | 19.5 GB | A | F | F | B |
Q4_0
| Resolution | VRAM Required | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 | 14.1 GB | S | D | F | A |
| 768×768 | 14.3 GB | S | D | F | A |
| 1024×1024 | 14.6 GB | S | D | F | A |
NF4
| Resolution | VRAM Required | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 | 14.1 GB | S | D | F | A |
| 768×768 | 14.3 GB | S | D | F | A |
| 1024×1024 | 14.6 GB | S | D | F | A |
Optimization Tips
GGUF Q4 available
Quantized GGUF format for lower VRAM and smaller downloads
Turbo / LCM distillation
Use distilled scheduler at 4-8 steps for faster iteration
Run with Python
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained(
"ideogram-ai/ideogram-4-fp8",
torch_dtype=torch.float16
)
pipe.to("cuda")
image = pipe(
prompt="a neon sign that reads 'OPEN'",
num_inference_steps=28,
guidance_scale=5.0,
height=1024,
width=1024,
).images[0]
image.save("output.png")Get started
Setup instructions for running Ideogram 4 locally
1. Download the model
Get the checkpoint from HuggingFace
2. Place in:
ComfyUI/models/checkpoints/ (or ComfyUI/models/unet/ for GGUF)3. Launch ComfyUI
python main.pyMemory Breakdown
VRAM allocation at 1024×1024 on RTX 4090 24GB (24 GB)
Estimated Generation Time
Time per image at 1024×1024, 28 steps, FP16.
Available Formats, Downloads & Setup
Download Ideogram 4 in the precision that matches your GPU. Lower precision usually means less VRAM pressure, while higher precision keeps more quality.
| Format | Präzision | Größe | Anbieter | |
|---|---|---|---|---|
| Offiziell quantisiert | ||||
| safetensorsEmpfohlenOffizielles FP8 | FP8 | 9.3 GB | official-fp8 | Herunterladen |
| safetensorsOffizielles FP8 | NF4 | 5.5 GB | official-nf4 | Herunterladen |
| Community-Konvertierungen | ||||
| ggufCommunity | Q4_K_M | 5.8 GB | community-gguf | Herunterladen |
LoRA Ecosystem
Growing EcosystemCommunity LoRAs (turbo, unconditional, style) available on Hugging Face and CivitAI.
Related Workflows
You might also like
Frequently asked questions
FAQ — Ideogram 4 VRAM, Runtimes & Fit
How much VRAM does Ideogram 4 need?
Ideogram 4 (9.3B parameters) requires approximately 37.7 GB of VRAM at FP16 precision for standard 1024×1024 image generation. If you want a lighter setup, lower precisions like FP8 can reduce memory use when available.
Can I run Ideogram 4 on an 8GB GPU?
Yes, Ideogram 4 can fit on some 8GB GPUs at ~5.8 GB at Q4_K_M. Check the VRAM table above for the exact resolution and precision trade-off.
Does Ideogram 4 work in ComfyUI and Diffusers?
Ideogram 4 is marked for ComfyUI and Diffusers support in our catalog, so those are the runtimes we recommend first for local setup. If your workflow uses another front end, check the model's available formats and workflow notes above before downloading.
Can I run Ideogram 4 on RTX 4090?
Ideogram 4 is too large for the RTX 4090's 24 GB VRAM at FP16. Consider using FP8 precision or a GPU with more VRAM.
Does Ideogram 4 support ControlNet?
There are currently no known ControlNet adapters for Ideogram 4. Check Hugging Face and Civitai for community-contributed adapters.
Does Ideogram 4 have LoRA support?
Community LoRAs (turbo, unconditional, style) available on Hugging Face and CivitAI. The LoRA ecosystem for Ideogram 4 is rated as "moderate". Each LoRA adds roughly 0.3 GB of extra VRAM.
How fast is Ideogram 4?
On a reference GPU (RTX 4090 24GB), Ideogram 4 generates a 1024×1024 image in approximately ~9s at FP16 with 28 inference steps. Faster GPUs with higher memory bandwidth will produce images more quickly.
About Ideogram 4
See also