GE

gemma-2b-bnb-gguf

GemmaGGUF by EllightUpdated 2024-05-08
Download on Hugging Face
Parameters2.51B
Context8K
Layers18
Architecturegemma
Smallest quant10.0 GB
Quick answer

gemma-2b-bnb-gguf needs about 10.7 GB of memory at F16 (a 10.0 GB file) with an 8K context window, so it fits on a 12 GB GPU.

gemma-2b-bnb-gguf is a 2.51B-parameter Gemma model in GGUF format, quantized by Ellight. Its trained context length is 8K tokens. The repository has 1 quant file, from 10.0 GB (F16) to 10.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1610.0 GB 10.7 GB
Too big Get file →

What GPU do you need for gemma-2b-bnb-gguf?

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 (10.0 GB file, about 10.7 GB in use).

Which gemma-2b-bnb-gguf quant should you choose?

F16 (10.0 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

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

Source

Quantized byEllight
FamilyGemma
Licenseapache-2.0
Downloads (HF)58
Last updated2024-05-08

Frequently asked questions about gemma-2b-bnb-gguf

How much VRAM does gemma-2b-bnb-gguf need?

About 10.7 GB at F16 with an 8K context window. That is the 10.0 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-2b-bnb-gguf on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma-2b-bnb-gguf GGUF?

It depends on the quant: F16 is 10.0 GB.

What context length does gemma-2b-bnb-gguf 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-2b-bnb-gguf GGUF?

The files are on Hugging Face in the Ellight/gemma-2b-bnb-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 gemma-2b-bnb-gguf 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.

Similar models

Browse all →

More Gemma models

All Gemma →

Other tiny models

All tiny models →