GE

Gelato 30B A3B

GelatoGGUF by noctrexUpdated 2025-11-10
Download on Hugging Face
Parameters30.5B
Context256K
Layers48
Architectureqwen3vlmoe
Smallest quant17.1 GB
Quick answer

Gelato 30B A3B needs about 18.4 GB of memory at MXFP4_MOE (a 17.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 17.1 GB (MXFP4_MOE) to 17.3 GB (IQ4_NL). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Gelato 30B A3B is a 30.5B-parameter Gelato model in GGUF format, quantized by noctrex. Its trained context length is 256K tokens. The repository has 2 quant files, from 17.1 GB (MXFP4_MOE) to 17.3 GB (IQ4_NL).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE17.1 GB 18.4 GB
Too big Get file →
IQ4_NL17.3 GB 18.6 GB
Too big Get file →

What GPU do you need for Gelato 30B A3B?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is IQ4_NL (17.3 GB file, about 18.6 GB in use).

Which Gelato 30B A3B quant should you choose?

MXFP4_MOE (17.1 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3vlmoe
Parameters30.5B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bynoctrex
FamilyGelato
Licenseapache-2.0
Downloads (HF)146
Last updated2025-11-10

Frequently asked questions about Gelato 30B A3B

How much VRAM does Gelato 30B A3B need?

About 18.4 GB at MXFP4_MOE with an 8K context window. That is the 17.1 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 Gelato 30B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gelato 30B A3B GGUF?

It depends on the quant: MXFP4_MOE is 17.1 GB, IQ4_NL is 17.3 GB.

What context length does Gelato 30B A3B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Gelato 30B A3B GGUF?

The files are on Hugging Face in the noctrex/Gelato-30B-A3B-i1-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 Gelato 30B A3B 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.

Other GGUFs of Gelato-30B-A3B

Similar models

Browse all →

More from noctrex

All by noctrex →

More Gelato models

All Gelato →

Other medium models

All medium models →