GE

DiscoPOP-zephyr-7b-gemma

GemmaGGUF by lmstudio-communityUpdated 2024-06-13
Download on Hugging Face
Parameters8.54B
Context8K
Layers28
Architecturegemma
Smallest quant5.7 GB
Quick answer

DiscoPOP-zephyr-7b-gemma needs about 10.5 GB of memory at Q4_K_M (a 6.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 5.7 GB (IQ4_XS) to 9.8 GB (Q8_0).

DiscoPOP-zephyr-7b-gemma is a 8.54B-parameter Gemma model in GGUF format, quantized by lmstudio-community. Its trained context length is 8K tokens. The repository has 5 quant files, from 5.7 GB (IQ4_XS) to 9.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS5.7 GB 10.0 GB
Too big Get file →
Q4_K_M6.3 GB 10.5 GB
Too big Get file →
Q5_K_M7.1 GB 11.3 GB
Too big Get file →
Q6_K7.9 GB 12.2 GB
Too big Get file →
Q8_09.8 GB 14.1 GB
Too big Get file →

What GPU do you need for DiscoPOP-zephyr-7b-gemma?

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 (7.1 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 14.1 GB in use).

Which DiscoPOP-zephyr-7b-gemma quant should you choose?

Q4_K_M is the usual starting point for DiscoPOP-zephyr-7b-gemma: it balances file size and quality well. Here it is a 6.3 GB file.

The Q8_0 file is 9.8 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ4_XS at 5.7 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

Architecturegemma
Parameters8.54B
Layers28
Trained context8,192 tokens
KV cache (fp16)448 KB per token

Source

Quantized bylmstudio-community
FamilyGemma
Licensegemma
Downloads (HF)320
Last updated2024-06-13

Frequently asked questions about DiscoPOP-zephyr-7b-gemma

How much VRAM does DiscoPOP-zephyr-7b-gemma need?

About 10.5 GB at Q4_K_M with an 8K context window. That is the 6.3 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 DiscoPOP-zephyr-7b-gemma on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DiscoPOP-zephyr-7b-gemma GGUF?

It depends on the quant: IQ4_XS is 5.7 GB, Q4_K_M is 6.3 GB, Q5_K_M is 7.1 GB, Q6_K is 7.9 GB, Q8_0 is 9.8 GB.

What context length does DiscoPOP-zephyr-7b-gemma support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.8 GB at 8K and 3.8 GB at 8K.

Where can I download DiscoPOP-zephyr-7b-gemma GGUF?

The files are on Hugging Face in the lmstudio-community/DiscoPOP-zephyr-7b-gemma-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 DiscoPOP-zephyr-7b-gemma 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.

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More Gemma models

All Gemma →

Other small models

All small models →