GE

Pocket Tiger Gemma 2B v1f Arm AArch64

GemmaGGUF by freakyXOUpdated 2024-08-12
Download on Hugging Face
Parameters2.61B
Context8K
Layers26
Architecturegemma2
Smallest quant1.6 GB
Quick answer

Pocket Tiger Gemma 2B v1f Arm AArch64 needs about 3.0 GB of memory at Q4_0 (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.6 GB (Q4_0) to 1.6 GB (Q4_0).

Pocket Tiger Gemma 2B v1f Arm AArch64 is a 2.61B-parameter Gemma model in GGUF format, quantized by freakyXO. Its trained context length is 8K tokens. The repository has 3 quant files, from 1.6 GB (Q4_0) to 1.6 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.6 GB 3.0 GB
Fits Get file →
Q4_01.6 GB 3.0 GB
Fits Get file →
Q4_01.6 GB 3.0 GB
Fits Get file →

What GPU do you need for Pocket Tiger Gemma 2B v1f Arm AArch64?

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 Q4_0 (1.6 GB file, about 3.0 GB in use).

Which Pocket Tiger Gemma 2B v1f Arm AArch64 quant should you choose?

Q4_0 (1.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q4_0 at 1.6 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

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 byfreakyXO
FamilyGemma
Downloads (HF)20
Last updated2024-08-12

Frequently asked questions about Pocket Tiger Gemma 2B v1f Arm AArch64

How much VRAM does Pocket Tiger Gemma 2B v1f Arm AArch64 need?

About 3.0 GB at Q4_0 with an 8K context window. That is the 1.6 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 Pocket Tiger Gemma 2B v1f Arm AArch64 on an 8 GB GPU?

Yes, with Q4_0: the 1.6 GB file needs about 3.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Pocket Tiger Gemma 2B v1f Arm AArch64 GGUF?

It depends on the quant: Q4_0 is 1.6 GB, Q4_0 is 1.6 GB, Q4_0 is 1.6 GB.

What context length does Pocket Tiger Gemma 2B v1f Arm AArch64 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 Pocket Tiger Gemma 2B v1f Arm AArch64 GGUF?

The files are on Hugging Face in the freakyXO/Pocket-Tiger-Gemma-2B-v1f-Arm-AArch64-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from freakyXO

All by freakyXO →

More Gemma models

All Gemma →

Other tiny models

All tiny models →