GE

RED50_Gemma_Instruct_model

GemmaGGUF by RainnighttramUpdated 2024-05-29
Download on Hugging Face
Parameters8.54B
Context8K
Layers28
Architecturegemma
Smallest quant5.3 GB
Quick answer

RED50_Gemma_Instruct_model needs about 9.6 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 5.3 GB (Q4_K_M) to 9.1 GB (Q8_0).

RED50_Gemma_Instruct_model is a 8.54B-parameter Gemma model in GGUF format, quantized by Rainnighttram. Its trained context length is 8K tokens. The repository has 2 quant files, from 5.3 GB (Q4_K_M) to 9.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M5.3 GB 9.6 GB
Too big Get file →
Q8_09.1 GB 13.3 GB
Too big Get file →

What GPU do you need for RED50_Gemma_Instruct_model?

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_M (5.3 GB file, about 9.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.1 GB file, about 13.3 GB in use).

Which RED50_Gemma_Instruct_model quant should you choose?

Q4_K_M is the usual starting point for RED50_Gemma_Instruct_model: it balances file size and quality well. Here it is a 5.3 GB file.

The Q8_0 file is 9.1 GB, about 1.7 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.

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 byRainnighttram
FamilyGemma
Licenseapache-2.0
Downloads (HF)74
Last updated2024-05-29

Frequently asked questions about RED50_Gemma_Instruct_model

How much VRAM does RED50_Gemma_Instruct_model need?

About 9.6 GB at Q4_K_M with an 8K context window. That is the 5.3 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 RED50_Gemma_Instruct_model on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of RED50_Gemma_Instruct_model GGUF?

It depends on the quant: Q4_K_M is 5.3 GB, Q8_0 is 9.1 GB.

What context length does RED50_Gemma_Instruct_model 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 RED50_Gemma_Instruct_model GGUF?

The files are on Hugging Face in the Rainnighttram/RED50_Gemma_Instruct_model repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does RED50_Gemma_Instruct_model use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of gemma-7b-it-bnb-4bit

Similar models

Browse all →

More from Rainnighttram

All by Rainnighttram →

More Gemma models

All Gemma →

Other small models

All small models →