IR

iris 3b GGUFs

IrisGGUF by realrebelaiUpdated 2026-10-09
Download on Hugging Face
Parameters3B
Context—
Layers—
Architectureiris
Smallest quant1.3 GB
Quick answer

iris 3b GGUFs needs about 2.4 GB of memory at Q4_K_S (a 1.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.3 GB (Q3_K_S) to 2.5 GB (Q6_K).

Iris‑3B GGUFs – 3‑billion‑parameter pixel‑space diffusion model

Iris‑3B GGUFs are quantized diffusion checkpoints for local image generation. The model outputs pixels directly, avoiding a VAE or latent decoder. It is available in several quantizations for use with ComfyUI.

Good at

  • Pixel‑space image generation
  • Dense vision tasks like depth estimation
  • Image restoration and upscaling

Limits

  • No LLM inference support
  • Requires ComfyUI custom nodes
  • No independent VRAM guarantees

Best for

  • Generating 1024×1024 images locally
  • Fine‑tuning for vision tasks
  • Rapid prototyping of diffusion pipelines

Who it’s for. Users who need a lightweight, local image generator that can be run in ComfyUI. Ideal for artists and developers who want to experiment with pixel‑space diffusion without a VAE.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S1.3 GB 1.9 GB
Fits Get file →
Q4_K_S1.7 GB 2.4 GB
Fits Get file →
Q5_K_S2.1 GB 2.8 GB
Fits Get file →
Q6_K2.5 GB 3.3 GB
Fits Get file →

For 8 GB VRAM, Q3_K_S (1.29 GB) is recommended; it uses about 1.9 GB at 8 k context. If more VRAM is available, Q4_K_S (1.69 GB, 2.4 GB) or Q5_K_S (2.06 GB, 2.8 GB) provide higher quality. Q6_K (2.46 GB, 3.3 GB) is best for maximum fidelity but needs more memory.

What GPU do you need for iris 3b GGUFs?

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 Q6_K (2.5 GB file, about 3.3 GB in use).

Which iris 3b GGUFs quant should you choose?

Q4_K_S (1.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q3_K_S at 1.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureiris
Parameters3B

Source

Quantized byrealrebelai
FamilyIris
Licenseapache-2.0
Downloads (HF)1,678
Last updated2026-10-09

Frequently asked questions about iris 3b GGUFs

How much VRAM does iris 3b GGUFs need?

About 2.4 GB at Q4_K_S with an 8K context window. That is the 1.7 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 GGUFs on an 8 GB GPU?

Yes, with Q6_K: the 2.5 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of iris 3b GGUFs GGUF?

It depends on the quant: Q3_K_S is 1.3 GB, Q4_K_S is 1.7 GB, Q5_K_S is 2.1 GB, Q6_K is 2.5 GB.

Where can I download iris 3b GGUFs GGUF?

The files are on Hugging Face in the realrebelai/iris-3b_GGUFs 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 GGUFs 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?

Yes, the Q3_K_S quantization is 1.29 GB and uses about 1.9 GB at 8 k context, fitting within 8 GB VRAM.

Does Iris‑3B support text prompts?

Iris‑3B uses a Qwen3‑VL text encoder; the GGUFs are diffusion checkpoints and require ComfyUI nodes for text prompt handling.

Is Iris‑3B an LLM?

No, Iris‑3B is a diffusion model for image generation, not a general‑purpose language model.

Other GGUFs of iris-3b

Similar models

Browse all →

More from realrebelai

All by realrebelai →

More Iris models

All Iris →

Other tiny models

All tiny models →