JA

Jais-3-0.9B

JaisGGUF by IFMUpdated 2026-10-27
Download on Hugging Face
Parameters1.08B
Context128K
Layers28
Architecturek2-horizon
Smallest quant0.7 GB
Quick answer

Jais-3-0.9B needs about 1.6 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.7 GB (Q4_K_M) to 2.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Jais-3-0.9B – a 0.9B decoder‑only model with 128K context

Jais-3-0.9B is a compact dense member of the Jais‑3 family. It offers a 128K token context window and is optimized for reasoning and tool usage. The model is available in multiple GGUF quantizations for llama.cpp and Ollama.

Good at

  • Reasoning tasks
  • Tool‑based interactions
  • Long‑form generation

Limits

  • No vision support
  • Requires recent llama.cpp build
  • Large VRAM needed for higher precision

Best for

  • Chatbots needing long context
  • Automated tool workflows
  • Research prototyping

Who it’s for. Developers and researchers who need a lightweight decoder‑only model with a large context window and built‑in reasoning and tool‑calling capabilities. The model is suitable for local deployment on systems with sufficient VRAM and a recent llama.cpp build.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.7 GB 1.6 GB
Fits Get file →
Q5_00.8 GB 1.7 GB
Fits Get file →
Q5_K_M0.8 GB 1.7 GB
Fits Get file →
Q6_K0.9 GB 1.9 GB
Fits Get file →
Q8_01.1 GB 2.1 GB
Fits Get file →
BF162.2 GB 3.1 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.67 GB file, ~1.6 GB memory). For 12 GB VRAM, Q5_0 or Q5_K_M (0.76–0.77 GB file, ~1.7 GB memory). For 16 GB VRAM, Q6_K (0.89 GB file, ~1.9 GB memory).

What GPU do you need for Jais-3-0.9B?

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: the best quant that fits is BF16 (2.2 GB file, about 3.1 GB in use).

Which Jais-3-0.9B quant should you choose?

Q4_K_M is the usual starting point for Jais-3-0.9B: it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 1.1 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

Architecturek2-horizon
Parameters1.08B
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized byIFM
FamilyJais
Licenseapache-2.0
Downloads (HF)666
Last updated2026-10-27

Frequently asked questions about Jais-3-0.9B

How much VRAM does Jais-3-0.9B need?

About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.7 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-3-0.9B on an 8 GB GPU?

Yes, with BF16: the 2.2 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Jais-3-0.9B GGUF?

It depends on the quant: Q4_K_M is 0.7 GB, Q5_0 is 0.8 GB, Q5_K_M is 0.8 GB, Q6_K is 0.9 GB, Q8_0 is 1.1 GB, BF16 is 2.2 GB.

What context length does Jais-3-0.9B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Jais-3-0.9B GGUF?

The files are on Hugging Face in the IFM/Jais-3-0.9B-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-3-0.9B 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.

Can I run Jais-3-0.9B on 8 GB VRAM?

Yes, the Q4_K_M quantization uses about 1.6 GB of VRAM at 8 k context, which fits within an 8 GB budget.

Does this model support image inputs?

No, Jais-3-0.9B does not have vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Jais-3-0.9B

Similar models

Browse all →

More from IFM

All by IFM →

More Jais models

All Jais →

Other tiny models

All tiny models →