GE

gemma-2-9b-it

GemmaGGUF by kolosalUpdated 2025-01-09
Download on Hugging Face
Parameters9.24B
Context8K
Layers42
Architecturegemma2
Smallest quant6.0 GB
Quick answer

gemma-2-9b-it needs about 13.1 GB of memory at Q8_0 (a 9.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 6.0 GB (Q4_K_L) to 37.0 GB (F32).

gemma-2-9b-it is a 9.24B-parameter Gemma model in GGUF format, quantized by kolosal. Its trained context length is 8K tokens. The repository has 3 quant files, from 6.0 GB (Q4_K_L) to 37.0 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_L6.0 GB 9.3 GB
Too big Get file →
Q8_09.8 GB 13.1 GB
Too big Get file →
F3237.0 GB 40.3 GB
Too big Get file →

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: 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 Q4_K_L (6.0 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 13.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 13.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 13.1 GB in use).
  • 48 GB VRAM: the best quant that fits is F32 (37.0 GB file, about 40.3 GB in use).

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

Q8_0 (9.8 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.

If memory is tight, the smallest file is Q4_K_L at 6.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

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 bykolosal
FamilyGemma
Downloads (HF)14
Last updated2025-01-09

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

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

About 13.1 GB at Q8_0 with an 8K context window. That is the 9.8 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?

Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q4_K_L is 6.0 GB, Q8_0 is 9.8 GB, F32 is 37.0 GB.

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 kolosal/gemma-2-9b 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 kolosal

All by kolosal →

More Gemma models

All Gemma →

Other small models

All small models →