EX

extGemma4 44B

ExtgemmaGGUF by Merlinoz11Updated 2026-07-03
Download on Hugging Face
Parameters44.2B
Context256K
Layers88
Architecturegemma4
Smallest quant21.8 GB
Quick answer

extGemma4 44B needs about 74.5 GB of memory at Q4_K_M (a 26.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 21.8 GB (Q3_K_M) to 46.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 189.0 GB.

extGemma4 44B is a 44.2B-parameter Extgemma model in GGUF format, quantized by Merlinoz11. Its trained context length is 256K tokens. The repository has 7 quant files, from 21.8 GB (Q3_K_M) to 46.9 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M21.8 GB 69.5 GB
Too big Get file →
Q4_K_S25.4 GB 73.1 GB
Too big Get file →
Q4_K_M26.8 GB 74.5 GB
Too big Get file →
Q5_K_S30.6 GB 78.3 GB
Too big Get file →
Q5_K_M31.4 GB 79.1 GB
Too big Get file →
Q6_K36.2 GB 84.0 GB
Too big Get file →
Q8_046.9 GB 94.7 GB
Too big Get file →

What GPU do you need for extGemma4 44B?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which extGemma4 44B quant should you choose?

Q4_K_M is the usual starting point for extGemma4 44B: it balances file size and quality well. Here it is a 26.8 GB file.

The Q8_0 file is 46.9 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 Q3_K_M at 21.8 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

Architecturegemma4
Parameters44.2B
Layers88
Trained context262,144 tokens
KV cache (fp16)5632 KB per token

Source

Quantized byMerlinoz11
FamilyExtgemma
Licenseapache-2.0
Downloads (HF)320
Last updated2026-07-03

Frequently asked questions about extGemma4 44B

How much VRAM does extGemma4 44B need?

About 74.5 GB at Q4_K_M with an 8K context window. That is the 26.8 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 extGemma4 44B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 69.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of extGemma4 44B GGUF?

It depends on the quant: Q3_K_M is 21.8 GB, Q4_K_S is 25.4 GB, Q4_K_M is 26.8 GB, Q5_K_S is 30.6 GB, Q5_K_M is 31.4 GB, Q6_K is 36.2 GB and 1 more.

What context length does extGemma4 44B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 47.2 GB at 8K and 189.0 GB at 32K.

Where can I download extGemma4 44B GGUF?

The files are on Hugging Face in the Merlinoz11/extGemma4-44B-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 extGemma4 44B 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 Merlinoz11

All by Merlinoz11 →

More Extgemma models

All Extgemma →

Other large models

All large models →