Ideogram 4 on Orange Pi AIpro (20T) (12 GB)

Can the Orange Pi AIpro (20T) (12 GB) run Ideogram 4?

Barely: it runs very slowly (tight fit · CPU offload)

Very slow (tight fit · CPU offload). At FP8 it needs about 8.9 GB of 9.8 GB usable and takes about 2.0 h per image.

Best precision: FP8
Memory mode: Sequential CPU offload
Time per image: 2.0 h
Output: 1024×1024, 48 steps

Best app to run it on the Orange Pi AIpro (20T) (12 GB)

On Linux on ARM boards

ComfyUI

Desktop app · runs on PyTorch (ComfyUI), GGUF via ComfyUI-GGUF

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Get ComfyUI

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Ideogram 4

Quantized files · GGUF for ComfyUI

Smaller GGUF versions for ComfyUI (with the ComfyUI-GGUF node). No sign-in needed; the model’s license still applies.

huggingface.co/leejet/ideogram-4-GGUF (opens in a new tab)

Original weights · Hugging Face

Full-precision files from Ideogram, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/ideogram-ai/ideogram-4-fp8 (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Official repo · GitHub

Reference code, inference scripts and docs from Ideogram. The weights themselves download from Hugging Face.

github.com/ideogram-oss/ideogram4 (opens in a new tab)

git clone https://github.com/ideogram-oss/ideogram4

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at FP8, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Very slowtight fit · CPU offload: How well it runs on the Orange Pi AIpro (20T) (12 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	40.6 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.6 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	66.1 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every precision on the Orange Pi AIpro (20T) (12 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	15.4 GB	9.8 GB	—	—	Won't run	92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	8.9 GB	9.8 GB	2.0 h	Sequential CPU offload	Very slowtight fit · CPU offload	90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`Q4 GGUF`	6.3 GB	9.8 GB	2.7 h	Sequential CPU offload	Very slowCPU offload	85Excellent quality (A+) · 85 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`NF4`	6.1 GB	9.8 GB	2.4 h	Sequential CPU offload	Very slowCPU offload	85Excellent quality (A+) · 85 of 100: how capable the model is at NF4, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Other hardware that runs it

92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell FP16 · 18 s · Runs well
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP8 · 19 s · Runs well (tight fit)
85Excellent quality (A+) · 85 of 100: how capable the model is at NF4, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 NF4 · 28 s · Runs well (tight fit)
85Excellent quality (A+) · 85 of 100: how capable the model is at NF4, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX NF4 · 31 s · Runs well (tight fit)
85Excellent quality (A+) · 85 of 100: how capable the model is at NF4, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT NF4 · 38 s · Runs well (encoder in RAM)
85Excellent quality (A+) · 85 of 100: how capable the model is at NF4, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 NF4 · 38 s · Runs well (encoder in RAM)

Quick answers

How much memory does Ideogram 4 need on the Orange Pi AIpro (20T) 12GB?

At FP8 it needs about 8.9 GB. The Orange Pi AIpro (20T) 12GB has 9.8 GB usable.

How long does Ideogram 4 take on the Orange Pi AIpro (20T) 12GB?

About 2.0 h per image at FP8 and default settings, an estimate scaled from a reference timing by this hardware’s compute speed.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.