IR

IRIS 18B GGUFS

IrisGGUF by jerrimuUpdated 2026-11-03
Download on Hugging Face
Parameters18B
Context128K
Layers28
Architectureernie4_5-moe
Smallest quant6.7 GB
Quick answer

IRIS 18B GGUFS needs about 11.9 GB of memory at Q4_K (a 10.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 6.7 GB (Q2_K) to 36.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

IRIS 18B GGUFS is a 18B-parameter Iris model in GGUF format, quantized by jerrimu. Its trained context length is 128K tokens. The repository has 4 quant files, from 6.7 GB (Q2_K) to 36.0 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K6.7 GB 7.6 GB
Tight Get file →
Q4_K10.9 GB 11.9 GB
Too big Get file →
Q8_019.1 GB 20.1 GB
Too big Get file →
BF1636.0 GB 37.0 GB
Too big Get file →

What GPU do you need for IRIS 18B GGUFS?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q2_K (6.7 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K (10.9 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K (10.9 GB file, about 11.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (19.1 GB file, about 20.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (19.1 GB file, about 20.1 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (36.0 GB file, about 37.0 GB in use).

Which IRIS 18B GGUFS quant should you choose?

Q4_K (10.9 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 Q2_K at 6.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureernie4_5-moe
Parameters18B (approximate, mixture of experts)
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized byjerrimu
FamilyIris
Licenseapache-2.0
Downloads (HF)207
Last updated2026-11-03

Frequently asked questions about IRIS 18B GGUFS

How much VRAM does IRIS 18B GGUFS need?

About 11.9 GB at Q4_K with an 8K context window. That is the 10.9 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 18B GGUFS on an 8 GB GPU?

Yes, with Q2_K: the 6.7 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of IRIS 18B GGUFS GGUF?

It depends on the quant: Q2_K is 6.7 GB, Q4_K is 10.9 GB, Q8_0 is 19.1 GB, BF16 is 36.0 GB.

What context length does IRIS 18B GGUFS support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download IRIS 18B GGUFS GGUF?

The files are on Hugging Face in the jerrimu/IRIS-18B-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 18B 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.

Similar models

Browse all →

More from jerrimu

All by jerrimu →

More Iris models

All Iris →

Other medium models

All medium models →