GE

Gelato 30B A3B

GelatoGGUF by mradermacherUpdated 2026-10-23
Download on Hugging Face
Parameters30.5B
Context256K
Layers48
Architectureqwen3vlmoe
Smallest quant11.3 GB
Quick answer

Gelato 30B A3B needs about 19.9 GB of memory at Q4_K_M (a 18.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 11.3 GB (Q2_K) to 32.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Gelato 30B A3B – a 30.5B parameter grounding model with vision and tools support

Gelato 30B A3B is a 30.5B parameter model built on the qwen3vlmoe architecture. It is a mixture of experts with 3B active parameters and is trained on 262144 context tokens. The model is released under the apache-2.0 license.

Good at

  • Vision‑guided GUI tasks
  • Tool‑use instruction following
  • Large context handling

Limits

  • No vision support in some quant variants
  • Large VRAM requirement for full precision
  • Requires 262144 token context for training data

Best for

  • GUI automation agents
  • Screen‑spotting applications
  • Computer‑use grounding tasks

Who it’s for. Developers building computer‑use agents or GUI automation tools. Researchers needing a grounding model that can interpret images and follow tool instructions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K11.3 GB 12.6 GB
Too big Get file →
Q3_K_S13.3 GB 14.6 GB
Too big Get file →
Q3_K_M14.7 GB 16.0 GB
Too big Get file →
Q3_K_L15.9 GB 17.2 GB
Too big Get file →
IQ4_XS16.6 GB 17.9 GB
Too big Get file →
Q4_K_S17.5 GB 18.8 GB
Too big Get file →
Q4_K_M18.6 GB 19.9 GB
Too big Get file →
Q5_K_S21.1 GB 22.4 GB
Too big Get file →
Q5_K_M21.7 GB 23.0 GB
Too big Get file →
Q6_K25.1 GB 26.4 GB
Too big Get file →
Q8_032.5 GB 33.8 GB
Too big Get file →

For 8 GB VRAM use Q4_K_S (file size 17.46 GB, estimated 18.8 GB memory). For 12 GB VRAM use Q5_K_M (21.73 GB, 23 GB memory). For 16 GB VRAM use Q6_K (25.09 GB, 26.4 GB memory).

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: the best quant that fits is Q3_K_M (14.7 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (21.7 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (25.1 GB file, about 26.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (32.5 GB file, about 33.8 GB in use).

Which Gelato 30B A3B quant should you choose?

Q4_K_M is the usual starting point for Gelato 30B A3B: it balances file size and quality well. Here it is a 18.6 GB file.

The Q8_0 file is 32.5 GB, about 1.8 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 Q2_K at 11.3 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

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

Source

Quantized bymradermacher
FamilyGelato
Licenseapache-2.0
Downloads (HF)958
Last updated2026-10-23

Frequently asked questions about Gelato 30B A3B

How much VRAM does Gelato 30B A3B need?

About 19.9 GB at Q4_K_M with an 8K context window. That is the 18.6 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 12.6 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: Q2_K is 11.3 GB, Q3_K_S is 13.3 GB, Q3_K_M is 14.7 GB, Q3_K_L is 15.9 GB, IQ4_XS is 16.6 GB, Q4_K_S is 17.5 GB and 5 more.

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 mradermacher/Gelato-30B-A3B-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.

Can I run Gelato 30B A3B on 8 GB VRAM?

Use the Q4_K_S quant; it requires about 18.8 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does the model support vision?

Yes, the model has detected vision ability and can process images.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Gelato-30B-A3B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gelato models

All Gelato →

Other medium models

All medium models →