GE

gemma 7b ko

GemmaGGUF by ij5Updated 2024-02-26
Download on Hugging Face
Parameters8.54B
Context8K
Layers28
Architecturellama
Smallest quant6.0 GB
Quick answer

gemma 7b ko needs about 9.4 GB of memory at Q5_K_M (a 6.0 GB file) with an 8K context window, so it fits on a 12 GB GPU.

gemma 7b ko is a 8.54B-parameter Gemma model in GGUF format, quantized by ij5. Its trained context length is 8K tokens. The repository has 1 quant file, from 6.0 GB (Q5_K_M) to 6.0 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M6.0 GB 9.4 GB
Too big Get file →

What GPU do you need for gemma 7b ko?

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 Q5_K_M (6.0 GB file, about 9.4 GB in use).

Which gemma 7b ko quant should you choose?

Q5_K_M (6.0 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.54B
Layers28
Trained context8,192 tokens
KV cache (fp16)336 KB per token

Source

Quantized byij5
FamilyGemma
Downloads (HF)19
Last updated2024-02-26

Frequently asked questions about gemma 7b ko

How much VRAM does gemma 7b ko need?

About 9.4 GB at Q5_K_M with an 8K context window. That is the 6.0 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 7b ko on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 7b ko GGUF?

It depends on the quant: Q5_K_M is 6.0 GB.

What context length does gemma 7b ko 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 7b ko GGUF?

The files are on Hugging Face in the ij5/gemma-7b-ko-gguf 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 ij5

All by ij5 →

More Gemma models

All Gemma →

Other small models

All small models →