GE

FuseChat Gemma 2 9B Instruct

GemmaGGUF by NikolayKozloffUpdated 2024-12-13
Download on Hugging Face
Parameters9.24B
Context8K
Layers42
Architecturegemma2
Smallest quant9.8 GB
Quick answer

FuseChat Gemma 2 9B Instruct 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.

FuseChat Gemma 2 9B Instruct is a 9.24B-parameter Gemma model in GGUF format, quantized by NikolayKozloff. Its trained context length is 8K tokens. The repository has 1 quant file, from 9.8 GB (Q8_0) to 9.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_09.8 GB 13.1 GB
Too big Get file →

What GPU do you need for FuseChat Gemma 2 9B Instruct?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 13.1 GB in use).

Which FuseChat Gemma 2 9B Instruct 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.

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 byNikolayKozloff
FamilyGemma
Downloads (HF)20
Last updated2024-12-13

Frequently asked questions about FuseChat Gemma 2 9B Instruct

How much VRAM does FuseChat Gemma 2 9B Instruct 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 FuseChat Gemma 2 9B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of FuseChat Gemma 2 9B Instruct GGUF?

It depends on the quant: Q8_0 is 9.8 GB.

What context length does FuseChat Gemma 2 9B Instruct 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 FuseChat Gemma 2 9B Instruct GGUF?

The files are on Hugging Face in the NikolayKozloff/FuseChat-Gemma-2-9B-Instruct-Q8_0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of FuseChat-Gemma-2-9B-Instruct

Similar models

Browse all →

More from NikolayKozloff

All by NikolayKozloff →

More Gemma models

All Gemma →

Other small models

All small models →