GE

gemma2 finetuning

GemmaGGUF by ball0428Updated 2024-09-24
Download on Hugging Face
Parameters2.61B
Context8K
Layers26
Architecturegemma2
Smallest quant2.8 GB
Quick answer

gemma2 finetuning 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.

gemma2 finetuning is a 2.61B-parameter Gemma model in GGUF format, quantized by ball0428. Its trained context length is 8K tokens. The repository has 1 quant file, from 2.8 GB (Q8_0) to 2.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_02.8 GB 4.2 GB
Fits Get file →

What GPU do you need for gemma2 finetuning?

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: the best quant that fits is Q8_0 (2.8 GB file, about 4.2 GB in use).

Which gemma2 finetuning 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.

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 byball0428
FamilyGemma
Downloads (HF)14
Last updated2024-09-24

Frequently asked questions about gemma2 finetuning

How much VRAM does gemma2 finetuning 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 gemma2 finetuning on an 8 GB GPU?

Yes, with Q8_0: the 2.8 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gemma2 finetuning GGUF?

It depends on the quant: Q8_0 is 2.8 GB.

What context length does gemma2 finetuning 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 gemma2 finetuning GGUF?

The files are on Hugging Face in the ball0428/gemma2_finetuning 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 ball0428

All by ball0428 →

More Gemma models

All Gemma →

Other tiny models

All tiny models →