IR

iris 3b

IrisGGUF by gguf-orgUpdated 2026-10-12
Download on Hugging Face
Parameters2.99B
Context—
Layers—
Architecturepig
Smallest quant2.5 GB
Quick answer

iris 3b needs about 3.4 GB of memory at its main file (a 2.5 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Iris 3B – a 3‑billion‑parameter pixel‑space vision model

Iris 3B is a 2.99‑billion‑parameter model that generates images by outputting every pixel directly. It can also perform dense vision tasks such as depth estimation and image restoration when fine‑tuned. The model is released under the Apache‑2.0 license.

Good at

  • Pixel‑space image generation
  • Dense vision tasks (depth, restoration)
  • Fine‑tuned for upscaling

Limits

  • No vision support in the base LLM interface
  • Requires 3.4 GB RAM at 8k context
  • Only one quantization available (unknown)

Best for

  • Generating 1024×1024 images quickly
  • Fine‑tuning for depth estimation
  • Image restoration and upscaling

Who it’s for. Developers and researchers needing a lightweight vision model that outputs pixel‑direct images. The model is suitable for integration into pipelines that require dense vision capabilities without a separate decoder.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.5 GB 3.4 GB
Fits Get file →

The only available GGUF file is 2.55 GB with an estimated 3.4 GB memory requirement at 8k context. This is the recommended quant for systems with at least 4 GB RAM. No other quantizations are listed.

What GPU do you need for iris 3b?

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 the main file (2.5 GB file, about 3.4 GB in use).

Specifications

Architecture from the GGUF header

Architecturepig
Parameters2.99B

Source

Quantized bygguf-org
FamilyIris
Licenseapache-2.0
Downloads (HF)874
Last updated2026-10-12

Frequently asked questions about iris 3b

How much VRAM does iris 3b need?

About 3.4 GB at its main file with an 8K context window. That is the 2.5 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 iris 3b on an 8 GB GPU?

Yes, with the smaller files: the 2.5 GB file needs about 3.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of iris 3b GGUF?

It depends on the quant: file is 2.5 GB.

Where can I download iris 3b GGUF?

The files are on Hugging Face in the gguf-org/iris-3b-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 iris 3b 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 Iris 3B on 8 GB VRAM?

The model requires approximately 3.4 GB of RAM at 8k context, so it can run on a system with 8 GB VRAM, assuming other processes do not consume excessive memory.

Does Iris 3B support vision tasks out of the box?

The base model focuses on pixel‑space image generation; vision tasks such as depth estimation and restoration require fine‑tuning.

What license applies to Iris 3B?

Iris 3B is released under the Apache‑2.0 license.

Other GGUFs of iris-3b

Similar models

Browse all →

More from gguf-org

All by gguf-org →

More Iris models

All Iris →

Other tiny models

All tiny models →