GE

gemma help tiny sft

GemmaGGUF by burtenshawUpdated 2024-08-09
Download on Hugging Face
Parameters2.51B
Context8K
Layers18
Architecturegemma
Smallest quant2.7 GB
Quick answer

gemma help tiny sft needs about 3.3 GB of memory at Q8_0 (a 2.7 GB file) with an 8K context window, so it fits on a 4 GB GPU.

gemma help tiny sft is a 2.51B-parameter Gemma model in GGUF format, quantized by burtenshaw. Its trained context length is 8K tokens. The repository has 1 quant file, from 2.7 GB (Q8_0) to 2.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_02.7 GB 3.3 GB
Fits Get file →

What GPU do you need for gemma help tiny sft?

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 Q8_0 (2.7 GB file, about 3.3 GB in use).

Which gemma help tiny sft quant should you choose?

Q8_0 (2.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma
Parameters2.51B
Layers18
Trained context8,192 tokens
KV cache (fp16)18 KB per token

Source

Quantized byburtenshaw
FamilyGemma
Licenseapache-2.0
Downloads (HF)42
Last updated2024-08-09

Frequently asked questions about gemma help tiny sft

How much VRAM does gemma help tiny sft need?

About 3.3 GB at Q8_0 with an 8K context window. That is the 2.7 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 gemma help tiny sft on an 8 GB GPU?

Yes, with Q8_0: the 2.7 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gemma help tiny sft GGUF?

It depends on the quant: Q8_0 is 2.7 GB.

What context length does gemma help tiny sft support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download gemma help tiny sft GGUF?

The files are on Hugging Face in the burtenshaw/gemma-help-tiny-sft repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does gemma help tiny sft 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-2b-bnb-4bit

Similar models

Browse all →

More from burtenshaw

All by burtenshaw →

More Gemma models

All Gemma →

Other tiny models

All tiny models →