JA

Jais-3-7B

JaisGGUF by webmp3Updated 2026-10-17
Download on Hugging Face
Parameters9B
Context512K
Layers36
Architecturek2-horizon
Smallest quant5.1 GB
Quick answer

Jais-3-7B needs about 7.3 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 5.1 GB (IQ4_XS) to 9.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Jais-3-7B is a 9B-parameter Jais model in GGUF format, quantized by webmp3. Its trained context length is 512K tokens. The repository has 5 quant files, from 5.1 GB (IQ4_XS) to 9.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS5.1 GB 6.8 GB
Fits Get file →
Q4_K_M5.6 GB 7.3 GB
Tight Get file →
Q5_K_M6.5 GB 8.2 GB
Too big Get file →
Q6_K7.4 GB 9.1 GB
Too big Get file →
Q8_09.6 GB 11.3 GB
Too big Get file →

What GPU do you need for Jais-3-7B?

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: the best quant that fits is Q4_K_M (5.6 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.6 GB file, about 11.3 GB in use).

Which Jais-3-7B quant should you choose?

Q4_K_M is the usual starting point for Jais-3-7B: it balances file size and quality well. Here it is a 5.6 GB file.

The Q8_0 file is 9.6 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.

If memory is tight, the smallest file is IQ4_XS at 5.1 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

Architecturek2-horizon
Parameters9B
Layers36
Trained context524,288 tokens
KV cache (fp16)144 KB per token

Source

Quantized bywebmp3
FamilyJais
Licenseapache-2.0
Downloads (HF)543
Last updated2026-10-17

Frequently asked questions about Jais-3-7B

How much VRAM does Jais-3-7B need?

About 7.3 GB at Q4_K_M with an 8K context window. That is the 5.6 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-3-7B on an 8 GB GPU?

Yes, with Q4_K_M: the 5.6 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Jais-3-7B GGUF?

It depends on the quant: IQ4_XS is 5.1 GB, Q4_K_M is 5.6 GB, Q5_K_M is 6.5 GB, Q6_K is 7.4 GB, Q8_0 is 9.6 GB.

What context length does Jais-3-7B support?

The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Jais-3-7B GGUF?

The files are on Hugging Face in the webmp3/Sakura-Jais-3-7B-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-3-7B 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.

Other GGUFs of Jais-3-7B

Similar models

Browse all →

More from webmp3

All by webmp3 →

More Jais models

All Jais →

Other small models

All small models →