GE

PE Type 2 Alma 4B

GemmaGGUF by vanta-researchUpdated 2026-03-01
Download on Hugging Face
Parameters3.88B
Context128K
Layers34
Architecturegemma3
Smallest quant7.8 GB
Quick answer

PE Type 2 Alma 4B needs about 9.4 GB of memory at F16 (a 7.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.

PE Type 2 Alma 4B is a 3.88B-parameter Gemma model in GGUF format, quantized by vanta-research. Its trained context length is 128K tokens. The repository has 1 quant file, from 7.8 GB (F16) to 7.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F167.8 GB 9.4 GB
Too big Get file →

What GPU do you need for PE Type 2 Alma 4B?

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: the best quant that fits is F16 (7.8 GB file, about 9.4 GB in use).

Which PE Type 2 Alma 4B quant should you choose?

F16 (7.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters3.88B
Layers34
Trained context131,072 tokens
KV cache (fp16)136 KB per token

Source

Quantized byvanta-research
FamilyGemma
Licenseapache-2.0
Downloads (HF)113
Last updated2026-03-01

Frequently asked questions about PE Type 2 Alma 4B

How much VRAM does PE Type 2 Alma 4B need?

About 9.4 GB at F16 with an 8K context window. That is the 7.8 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 PE Type 2 Alma 4B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of PE Type 2 Alma 4B GGUF?

It depends on the quant: F16 is 7.8 GB.

What context length does PE Type 2 Alma 4B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.

Where can I download PE Type 2 Alma 4B GGUF?

The files are on Hugging Face in the vanta-research/PE-Type-2-Alma-4B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does PE Type 2 Alma 4B 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 gemma-3-4b-it

Similar models

Browse all →

More from vanta-research

All by vanta-research →

More Gemma models

All Gemma →

Other small models

All small models →