OM

omnigen2

OmnigenGGUF by calcuisUpdated 2025-08-07
Download on Hugging Face
Parameters3.97B
Context—
Layers—
Architecturepig
Smallest quant0.2 GB
Quick answer

omnigen2 needs about 7.2 GB of memory at Q4_K_M (a 6.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 20 quants, from 0.2 GB (F16) to 15.9 GB (F32).

OmniGen2 – a multimodal model with text and image decoding pathways

OmniGen2 is a multimodal generation model with separate decoding pathways for text and image. It supports visual understanding, text‑to‑image generation, instruction‑guided image editing, and in‑context generation. The model is open‑source and available in multiple GGUF quantizations.

Good at

  • Text‑to‑image generation
  • Instruction‑guided image editing
  • In‑context visual generation

Limits

  • No vision support in some quantizations
  • Requires 8k context for memory estimates
  • License is apache‑2.0

Best for

  • Generating images from prompts
  • Editing images with text instructions
  • Combining text and image inputs for creative output

Who it’s for. Developers and researchers needing a unified multimodal model for text and image tasks. The model is suitable for projects that require both generation and editing capabilities within a single framework.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.2 GB 0.7 GB
Fits Get file →
Q6_K3.2 GB 4.1 GB
Fits Get file →
IQ4_NL3.5 GB 4.4 GB
Fits Get file →
Q2_K5.7 GB 6.8 GB
Fits Get file →
Q3_K_M5.8 GB 7.0 GB
Fits Get file →
Q3_K_M5.8 GB 7.0 GB
Fits Get file →
Q4_K_M6.0 GB 7.2 GB
Fits Get file →
IQ4_NL6.0 GB 7.2 GB
Fits Get file →
Q4_06.0 GB 7.2 GB
Fits Get file →
Q4_K_M6.0 GB 7.2 GB
Tight Get file →
Q4_16.1 GB 7.3 GB
Tight Get file →
Q5_K_M6.1 GB 7.4 GB
Tight Get file →
Q5_06.2 GB 7.4 GB
Tight Get file →
Q5_K_M6.2 GB 7.4 GB
Tight Get file →
Q5_16.2 GB 7.5 GB
Tight Get file →
Q6_K6.3 GB 7.6 GB
Tight Get file →
Q8_06.7 GB 8.0 GB
Tight Get file →
BF167.9 GB 9.4 GB
Too big Get file →
F167.9 GB 9.4 GB
Too big Get file →
F3215.9 GB 18.3 GB
Too big Get file →

For 8 GB VRAM, use Q6_K (file size 3.25 GB, estimated 4.1 GB memory). If 16 GB VRAM is available, Q4_K_M (file size 5.98 GB, estimated 7.2 GB memory) offers a good balance. For larger budgets, BF16 (file size 7.94 GB, estimated 9.4 GB memory) provides higher precision.

What GPU do you need for omnigen2?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F16 (0.2 GB file, about 0.7 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_NL (3.5 GB file, about 4.4 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (6.7 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (7.9 GB file, about 9.4 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (7.9 GB file, about 9.4 GB in use).
  • 24 GB VRAM: the best quant that fits is F32 (15.9 GB file, about 18.3 GB in use).

Which omnigen2 quant should you choose?

Q4_K_M is the usual starting point for omnigen2: it balances file size and quality well. Here it is a 6.0 GB file.

The Q8_0 file is 6.7 GB, about 1.1 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is F16 at 0.2 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturepig
Parameters3.97B

Source

Quantized bycalcuis
FamilyOmnigen
Licenseapache-2.0
Downloads (HF)1,302
Last updated2025-08-07

Frequently asked questions about omnigen2

How much VRAM does omnigen2 need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 6.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run omnigen2 on an 8 GB GPU?

Yes, with Q8_0: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of omnigen2 GGUF?

It depends on the quant: F16 is 0.2 GB, Q6_K is 3.2 GB, IQ4_NL is 3.5 GB, Q2_K is 5.7 GB, Q3_K_M is 5.8 GB, Q3_K_M is 5.8 GB and 14 more.

Where can I download omnigen2 GGUF?

The files are on Hugging Face in the calcuis/omnigen2-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does omnigen2 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run OmniGen2 on 8 GB VRAM?

Yes, the Q6_K quantization requires about 4.1 GB memory at 8k context, which fits within 8 GB VRAM.

Does OmniGen2 support vision tasks?

Yes, it includes visual understanding and image generation capabilities as part of its multimodal design.

Similar models

Browse all →

More from calcuis

All by calcuis →

Other small models

All small models →