GE

Gemma 2 2B Instruct structured output

GemmaGGUF by bastienpUpdated 2024-08-19
Download on Hugging Face
Parameters2.61B
Context8K
Layers26
Architecturegemma2
Smallest quant1.7 GB
Quick answer

Gemma 2 2B Instruct structured output needs about 3.1 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.7 GB (Q4_K_M) to 5.2 GB (F16).

Gemma 2 2B Instruct structured output is a 2.61B-parameter Gemma model in GGUF format, quantized by bastienp. Its trained context length is 8K tokens. The repository has 4 quant files, from 1.7 GB (Q4_K_M) to 5.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.7 GB 3.1 GB
Fits Get file →
Q5_K_M1.9 GB 3.3 GB
Fits Get file →
Q8_02.8 GB 4.2 GB
Fits Get file →
F165.2 GB 6.6 GB
Fits Get file →

What GPU do you need for Gemma 2 2B Instruct structured output?

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 Q5_K_M (1.9 GB file, about 3.3 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 F16 (5.2 GB file, about 6.6 GB in use).

Which Gemma 2 2B Instruct structured output quant should you choose?

Q4_K_M is the usual starting point for Gemma 2 2B Instruct structured output: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 2.8 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

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 bybastienp
FamilyGemma
Licensegemma
Downloads (HF)133
Last updated2024-08-19

Frequently asked questions about Gemma 2 2B Instruct structured output

How much VRAM does Gemma 2 2B Instruct structured output need?

About 3.1 GB at Q4_K_M with an 8K context window. That is the 1.7 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 2 2B Instruct structured output on an 8 GB GPU?

Yes, with F16: 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 Gemma 2 2B Instruct structured output GGUF?

It depends on the quant: Q4_K_M is 1.7 GB, Q5_K_M is 1.9 GB, Q8_0 is 2.8 GB, F16 is 5.2 GB.

What context length does Gemma 2 2B Instruct structured output 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 Gemma 2 2B Instruct structured output GGUF?

The files are on Hugging Face in the bastienp/Gemma-2-2B-Instruct-structured-output 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 2 2B Instruct structured output use?

Hugging Face lists the license as gemma. 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-2-2b-it

Similar models

Browse all →

More Gemma models

All Gemma →

Other tiny models

All tiny models →