GE

gemma-2-9b-it

GemmaGGUF by qwp4w3hybUpdated 2024-07-02
Download on Hugging Face
Parameters9.24B
Context8K
Layers42
Architecturegemma2
Smallest quant2.4 GB
Quick answer

gemma-2-9b-it needs about 10.2 GB of memory at Q4_K_L (a 6.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 9 quants, from 2.4 GB (IQ1_S) to 18.5 GB (BF16).

Gemma‑2‑9b‑it: 9.24B parameter LLM with 8192 token context

Gemma‑2‑9b‑it is a 9.24B parameter language model based on the Gemma2 architecture. It supports up to 8192 training context tokens and is available in multiple GGUF quantizations. The model is released under the gemma license.

Good at

  • Large context reasoning
  • Multilingual text generation
  • Fine‑tuned instruction following

Limits

  • No vision support
  • Requires 8k context for full performance
  • License restricts commercial use

Best for

  • Chatbots needing long context
  • Research on instruction‑tuned LLMs
  • Generating technical documentation

Who it’s for. Developers and researchers who need a large‑parameter LLM with extended context. The model is suitable for applications that can run on GPU or CPU with sufficient memory and comply with the gemma license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.4 GB 5.7 GB
Fits Get file →
IQ2_XXS2.8 GB 6.1 GB
Fits Get file →
IQ3_XXS3.8 GB 7.1 GB
Fits Get file →
IQ4_XS5.2 GB 8.5 GB
Too big Get file →
Q4_K_L6.8 GB 10.2 GB
Too big Get file →
Q5_K_L7.7 GB 11.0 GB
Too big Get file →
Q6_K_L8.7 GB 12.0 GB
Too big Get file →
Q8_010.7 GB 14.0 GB
Too big Get file →
BF1618.5 GB 21.8 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (2.38 GB, 5.7 GB memory at 8k context) or IQ2_XXS (2.82 GB, 6.1 GB). For 12‑GB VRAM, Q4_K_L (6.84 GB, 10.2 GB) or Q5_K_L (7.73 GB, 11 GB) provide a good balance. Higher‑precision BF16 (18.49 GB, 21.8 GB) offers best quality but needs more memory.

What GPU do you need for 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 IQ1_S (2.4 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_XXS (3.8 GB file, about 7.1 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K_L (8.7 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (10.7 GB file, about 14.0 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (18.5 GB file, about 21.8 GB in use).

Which gemma-2-9b-it quant should you choose?

Q4_K_L (6.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is IQ1_S at 2.4 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 byqwp4w3hyb
FamilyGemma
Licensegemma
Downloads (HF)984
Last updated2024-07-02

Frequently asked questions about gemma-2-9b-it

How much VRAM does gemma-2-9b-it need?

About 10.2 GB at Q4_K_L with an 8K context window. That is the 6.8 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 gemma-2-9b-it on an 8 GB GPU?

Yes, with IQ3_XXS: the 3.8 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gemma-2-9b-it GGUF?

It depends on the quant: IQ1_S is 2.4 GB, IQ2_XXS is 2.8 GB, IQ3_XXS is 3.8 GB, IQ4_XS is 5.2 GB, Q4_K_L is 6.8 GB, Q5_K_L is 7.7 GB and 3 more.

What context length does 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 gemma-2-9b-it GGUF?

The files are on Hugging Face in the qwp4w3hyb/gemma-2-9b-it-iMat-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-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 Gemma‑2‑9b‑it on 8 GB VRAM?

Yes, using IQ1_S or IQ2_XXS quantizations, which fit within 8 GB VRAM and use about 5.7–6.1 GB memory at 8k context.

Does Gemma‑2‑9b‑it support vision tasks?

No, the model has no vision capabilities and is text‑only.

What is the maximum context length for this model?

The model supports up to 8192 training context tokens.

Other GGUFs of gemma-2-9b-it

Similar models

Browse all →

More from qwp4w3hyb

All by qwp4w3hyb →

More Gemma models

All Gemma →

Other small models

All small models →