GE

GemmaX2 28 2B v0.1

GemmaGGUF by TonicUpdated 2025-03-02
Download on Hugging Face
Parameters2.61B
Context8K
Layers26
Architecturegemma2
Smallest quant1.6 GB
Quick answer

GemmaX2 28 2B v0.1 needs about 4.2 GB of memory at Q8_0 (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 1.6 GB (TQ1_0) to 5.2 GB (F16).

GemmaX2 28 2B v0.1 is a 2.61B-parameter Gemma model in GGUF format, quantized by Tonic. Its trained context length is 8K tokens. The repository has 5 quant files, from 1.6 GB (TQ1_0) to 5.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_01.6 GB 3.0 GB
Fits Get file →
TQ2_01.7 GB 3.1 GB
Fits Get file →
Q8_02.8 GB 4.2 GB
Fits Get file →
BF165.2 GB 6.6 GB
Fits Get file →
F165.2 GB 6.6 GB
Fits Get file →

What GPU do you need for GemmaX2 28 2B v0.1?

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: the best quant that fits is TQ2_0 (1.7 GB file, about 3.1 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.8 GB file, about 4.2 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (5.2 GB file, about 6.6 GB in use).

Which GemmaX2 28 2B v0.1 quant should you choose?

Q8_0 (2.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is TQ1_0 at 1.6 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma2
Parameters2.61B
Layers26
Trained context8,192 tokens
KV cache (fp16)104 KB per token

Source

Quantized byTonic
FamilyGemma
Licenseapache-2.0
Downloads (HF)121
Last updated2025-03-02

Frequently asked questions about GemmaX2 28 2B v0.1

How much VRAM does GemmaX2 28 2B v0.1 need?

About 4.2 GB at Q8_0 with an 8K context window. That is the 2.8 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 GemmaX2 28 2B v0.1 on an 8 GB GPU?

Yes, with BF16: the 5.2 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GemmaX2 28 2B v0.1 GGUF?

It depends on the quant: TQ1_0 is 1.6 GB, TQ2_0 is 1.7 GB, Q8_0 is 2.8 GB, BF16 is 5.2 GB, F16 is 5.2 GB.

What context length does GemmaX2 28 2B v0.1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.9 GB at 8K.

Where can I download GemmaX2 28 2B v0.1 GGUF?

The files are on Hugging Face in the Tonic/GemmaX2-28-2B-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 GemmaX2 28 2B v0.1 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 GemmaX2-28-2B-v0.1

Similar models

Browse all →

More from Tonic

All by Tonic →

More Gemma models

All Gemma →

Other tiny models

All tiny models →