GE

Google_Gemma_2_9b_it

GemmaGGUF by NexesenexUpdated 2024-08-20
Download on Hugging Face
Parameters9.24B
Context8K
Layers42
Architecturegemma2
Smallest quant2.3 GB
Quick answer

Google_Gemma_2_9b_it needs about 9.1 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 2.3 GB (IQ1_XS) to 6.6 GB (Q5_K_M).

Google Gemma 2 9b it in GGUF format

Google Gemma 2 9b it is a 9.24‑billion parameter model. It supports a 8192 token context window and is available in multiple experimental quantizations. The model is released under the gemma license.

Good at

  • Large context handling
  • Experimental quantization support
  • Multi‑language data

Limits

  • No vision support
  • License restricts commercial use
  • Requires 8k context for memory estimates

Best for

  • Chatbot development
  • Text generation tasks
  • Research prototyping

Who it’s for. Developers and researchers needing a large‑context LLM with flexible quantization. The model is suitable for those who can manage the memory requirements and comply with the gemma license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_XS2.3 GB 5.7 GB
Fits Get file →
IQ1_S2.4 GB 5.8 GB
Fits Get file →
IQ1_M2.6 GB 5.9 GB
Fits Get file →
—2.7 GB 6.0 GB
Fits Get file →
IQ2_XXS2.9 GB 6.2 GB
Fits Get file →
IQ2_XS3.1 GB 6.4 GB
Fits Get file →
IQ2_S3.2 GB 6.5 GB
Fits Get file →
IQ2_M3.4 GB 6.7 GB
Fits Get file →
—3.6 GB 7.0 GB
Fits Get file →
IQ3_XXS3.9 GB 7.2 GB
Fits Get file →
Q2_K_L4.0 GB 7.3 GB
Tight Get file →
IQ3_XS4.1 GB 7.4 GB
Tight Get file →
IQ3_XS4.2 GB 7.5 GB
Tight Get file →
IQ3_S4.4 GB 7.7 GB
Tight Get file →
IQ3_M4.5 GB 7.9 GB
Tight Get file →
—4.8 GB 8.2 GB
Too big Get file →
IQ4_XS5.3 GB 8.6 GB
Too big Get file →
Q4_K_S5.5 GB 8.8 GB
Too big Get file →
Q4_K_M5.8 GB 9.1 GB
Too big Get file →
Q5_K_S6.5 GB 9.8 GB
Too big Get file →
Q5_K_M6.6 GB 10.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_XS or IQ1_S (est. 5.7‑5.8 GB). For 12 GB VRAM, IQ2_M or Q4_K_M (est. 6.7‑9.1 GB). Larger models like Q5_K_M need 10 GB VRAM or more.

What GPU do you need for Google_Gemma_2_9b_it?

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 the main file (2.7 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_M (4.5 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (6.6 GB file, about 10.0 GB in use).

Which Google_Gemma_2_9b_it quant should you choose?

Q4_K_M is the usual starting point for Google_Gemma_2_9b_it: it balances file size and quality well. Here it is a 5.8 GB file.

If memory is tight, the smallest file is IQ1_XS at 2.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma2
Parameters9.24B
Layers42
Trained context8,192 tokens
KV cache (fp16)336 KB per token

Source

Quantized byNexesenex
FamilyGemma
Licensegemma
Downloads (HF)760
Last updated2024-08-20

Frequently asked questions about Google_Gemma_2_9b_it

How much VRAM does Google_Gemma_2_9b_it need?

About 9.1 GB at Q4_K_M with an 8K context window. That is the 5.8 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 Google_Gemma_2_9b_it on an 8 GB GPU?

Yes, with IQ3_M: the 4.5 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Google_Gemma_2_9b_it GGUF?

It depends on the quant: IQ1_XS is 2.3 GB, IQ1_S is 2.4 GB, IQ1_M is 2.6 GB, file is 2.7 GB, IQ2_XXS is 2.9 GB, IQ2_XS is 3.1 GB and 15 more.

What context length does Google_Gemma_2_9b_it support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.8 GB at 8K and 2.8 GB at 8K.

Where can I download Google_Gemma_2_9b_it GGUF?

The files are on Hugging Face in the Nexesenex/Google_Gemma-2-9b-it_iMat_Custom_Quant_Stategies-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 Google_Gemma_2_9b_it 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.

Can I run this model on 8 GB VRAM?

Yes, the IQ1_XS and IQ1_S quantizations use about 5.7‑5.8 GB at 8k context, fitting within 8 GB VRAM.

Does this model support vision tasks?

No, the model has no vision capabilities.

What languages does it support?

The quantizations include French, Serbian, and Croatian data, but no explicit language list is provided.

Similar models

Browse all →

More from Nexesenex

All by Nexesenex →

More Gemma models

All Gemma →

Other small models

All small models →