AR

Arabic chat 7B

ArabicGGUF by ISTNetworksUpdated 2024-05-28
Download on Hugging Face
Parameters6.95B
Context4K
Layers32
Architecturellama
Smallest quant4.9 GB
Quick answer

Arabic chat 7B needs about 9.7 GB of memory at Q5_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 12 GB GPU.

Arabic chat 7B is a 6.95B-parameter Arabic model in GGUF format, quantized by ISTNetworks. Its trained context length is 4K tokens. The repository has 1 quant file, from 4.9 GB (Q5_K_M) to 4.9 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M4.9 GB 7.6 GB
Tight Get file →

What GPU do you need for Arabic chat 7B?

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 (4.9 GB file, about 9.7 GB in use).

Which Arabic chat 7B quant should you choose?

Q5_K_M (4.9 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
Parameters6.95B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byISTNetworks
FamilyArabic
Licenseapache-2.0
Downloads (HF)149
Last updated2024-05-28

Frequently asked questions about Arabic chat 7B

How much VRAM does Arabic chat 7B need?

About 9.7 GB at Q5_K_M with an 8K context window. That is the 4.9 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 Arabic chat 7B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Arabic chat 7B GGUF?

It depends on the quant: Q5_K_M is 4.9 GB.

What context length does Arabic chat 7B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Arabic chat 7B GGUF?

The files are on Hugging Face in the ISTNetworks/Arabic_chat_7B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Arabic chat 7B 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.

Similar models

Browse all →

More from ISTNetworks

All by ISTNetworks →

More Arabic models

All Arabic →

Other small models

All small models →