JA

Jais Family 13b Chat

JaisGGUF by mradermacherUpdated 2025-03-06
Download on Hugging Face
Parameters13.5B
Context2K
Layers40
Architecturejais
Smallest quant4.0 GB
Quick answer

Jais Family 13b Chat needs about 16.2 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 4.0 GB (IQ1_S) to 11.7 GB (Q6_K).

Jais Family 13b Chat – 13.5B parameter bilingual English‑Arabic LLM

The Jais Family 13b Chat is a 13.5B parameter transformer model trained from scratch on Arabic and English data. It is instruction fine‑tuned for dialogue and supports coding tasks. The model is released under the Apache‑2.0 license.

Good at

  • Bilingual English‑Arabic dialogue
  • Coding assistance
  • Contextual text generation

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • Large VRAM needed for higher quants

Best for

  • Chatbot development
  • Code generation tools
  • Multilingual content creation

Who it’s for. Developers building Arabic‑English applications or researchers needing a bilingual LLM. The model is suitable for teams that can allocate sufficient GPU memory for the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.0 GB 6.2 GB
Fits Get file →
IQ1_M4.2 GB 6.4 GB
Fits Get file →
IQ2_XXS4.6 GB 6.7 GB
Fits Get file →
IQ2_XS4.9 GB 7.0 GB
Fits Get file →
IQ2_S5.1 GB 7.2 GB
Tight Get file →
IQ2_M5.3 GB 7.5 GB
Tight Get file →
Q2_K_S5.3 GB 7.5 GB
Tight Get file →
Q2_K5.4 GB 7.6 GB
Tight Get file →
IQ3_XXS5.9 GB 8.1 GB
Too big Get file →
IQ3_XS6.1 GB 8.3 GB
Too big Get file →
IQ3_S6.3 GB 8.5 GB
Too big Get file →
Q3_K_S6.3 GB 8.5 GB
Too big Get file →
IQ3_M6.9 GB 9.1 GB
Too big Get file →
Q3_K_M7.3 GB 9.4 GB
Too big Get file →
IQ4_XS7.4 GB 9.6 GB
Too big Get file →
Q3_K_L7.6 GB 9.7 GB
Too big Get file →
IQ4_NL7.7 GB 9.9 GB
Too big Get file →
Q4_07.7 GB 9.9 GB
Too big Get file →
Q4_K_S8.1 GB 10.2 GB
Too big Get file →
Q4_18.5 GB 10.7 GB
Too big Get file →
Q4_K_M9.0 GB 11.1 GB
Too big Get file →
Q5_K_S9.5 GB 11.7 GB
Too big Get file →
Q5_K_M10.4 GB 12.5 GB
Too big Get file →
Q6_K11.7 GB 13.9 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (4.01 GB file, ~11.2 GB memory at 8k context). For 12‑GB VRAM, IQ2_XS (4.86 GB file, ~12.1 GB memory). For 16‑GB VRAM, Q4_K_M (8.97 GB file, ~16.2 GB memory). Estimates are approximate.

What GPU do you need for Jais Family 13b Chat?

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 IQ2_XXS (4.6 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (8.5 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (11.7 GB file, about 18.9 GB in use).

Which Jais Family 13b Chat quant should you choose?

Q4_K_M is the usual starting point for Jais Family 13b Chat: it balances file size and quality well. Here it is a 9.0 GB file.

If memory is tight, the smallest file is IQ1_S at 4.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturejais
Parameters13.5B
Layers40
Trained context2,048 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymradermacher
FamilyJais
Licenseapache-2.0
Downloads (HF)1,181
Last updated2025-03-06

Frequently asked questions about Jais Family 13b Chat

How much VRAM does Jais Family 13b Chat need?

About 16.2 GB at Q4_K_M with an 8K context window. That is the 9.0 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 Family 13b Chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Jais Family 13b Chat GGUF?

It depends on the quant: IQ1_S is 4.0 GB, IQ1_M is 4.2 GB, IQ2_XXS is 4.6 GB, IQ2_XS is 4.9 GB, IQ2_S is 5.1 GB, IQ2_M is 5.3 GB and 18 more.

What context length does Jais Family 13b Chat support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 6.7 GB at 8K and 1.7 GB at 2K.

Where can I download Jais Family 13b Chat GGUF?

The files are on Hugging Face in the mradermacher/jais-family-13b-chat-i1-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 Family 13b Chat 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 Family 13b Chat on 8 GB VRAM?

Yes, using the IQ1_S quantization which requires about 11.2 GB of VRAM at 8k context.

Does the model support vision tasks?

No, the model is text‑only and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of jais-family-13b-chat

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Jais models

All Jais →

Other medium models

All medium models →