JA

jais-30b-chat-v1

JaisGGUF by dormoshUpdated 2024-07-15
Download on Hugging Face
Parameters30.8B
Context2K
Layers48
Architecturejais
Smallest quant38.9 GB
Quick answer

jais-30b-chat-v1 needs about 50.7 GB of memory at Q8_0 (a 38.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 38.9 GB (Q8_0) to 61.6 GB (F16).

jais-30b-chat-v1 is a 30.8B-parameter Jais model in GGUF format, quantized by dormosh. Its trained context length is 2K tokens. The repository has 2 quant files, from 38.9 GB (Q8_0) to 61.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_038.9 GB 42.2 GB
Too big Get file →
F1661.6 GB (3 parts) 65.0 GB
Too big Get file →

What GPU do you need for jais-30b-chat-v1?

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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which jais-30b-chat-v1 quant should you choose?

Q8_0 (38.9 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

Architecturejais
Parameters30.8B
Layers48
Trained context2,048 tokens
KV cache (fp16)1344 KB per token

Source

Quantized bydormosh
FamilyJais
Licenseapache-2.0
Downloads (HF)20
Last updated2024-07-15

Frequently asked questions about jais-30b-chat-v1

How much VRAM does jais-30b-chat-v1 need?

About 50.7 GB at Q8_0 with an 8K context window. That is the 38.9 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 jais-30b-chat-v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 50.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of jais-30b-chat-v1 GGUF?

It depends on the quant: Q8_0 is 38.9 GB, F16 is 61.6 GB.

What context length does jais-30b-chat-v1 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 11.3 GB at 8K and 2.8 GB at 2K.

Where can I download jais-30b-chat-v1 GGUF?

The files are on Hugging Face in the dormosh/jais-30b-chat-v1-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 jais-30b-chat-v1 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 dormosh

All by dormosh →

More Jais models

All Jais →

Other medium models

All medium models →