Can the LattePanda Sigma (32 GB) run OmniGen2?

Barely: it runs very slowly

Very slow. At FP8 it needs about 10.3 GB of 16.0 GB usable and takes about 4.4 min per image.

Best precision: FP8
Memory mode: Everything on GPU
Time per image: 4.4 min
Output: 1024×1024, 50 steps

Best app to run it on the LattePanda Sigma (32 GB)

On Windows

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

On Linux

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 OmniGen2

Original weights · Hugging Face

Full-precision files from BAAI (VectorSpaceLab), for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/OmniGen2/OmniGen2 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from BAAI (VectorSpaceLab). The weights themselves download from Hugging Face.

github.com/VectorSpaceLab/OmniGen2 (opens in a new tab)

git clone https://github.com/VectorSpaceLab/OmniGen2

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 64Good quality (B) · 64 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (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 slow: How well it runs on the LattePanda Sigma (32 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.	29.1 / 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.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	2.9 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	14.9 / 15
Match score	71.9 / 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 LattePanda Sigma (32 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	10.5 GB	16.0 GB	5.2 min	Text encoder offloaded	Very slowencoder unloaded after use	66Good quality (B) · 66 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	10.3 GB	16.0 GB	4.4 min	Everything on GPU	Very slow	64Good quality (B) · 64 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Other hardware that runs it

64Good quality (B) · 64 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT FP8 · 19 s · Runs well
64Good quality (B) · 64 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 FP8 · 19 s · Runs well
64Good quality (B) · 64 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER FP8 · 20 s · Runs well
64Good quality (B) · 64 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER FP8 · 23 s · Runs well
64Good quality (B) · 64 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti FP8 · 23 s · Runs well
66Good quality (B) · 66 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 FP16 · 30 s · Runs well

Quick answers

How much memory does OmniGen2 need on the LattePanda Sigma 32GB?

At FP8 it needs about 10.3 GB. The LattePanda Sigma 32GB has 16.0 GB usable.

How long does OmniGen2 take on the LattePanda Sigma 32GB?

About 4.4 min 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.