JA

Jais Family 30b 16k Chat

JaisGGUF by mradermacherUpdated 2025-03-05
Download on Hugging Face
Parameters30.8B
Context16K
Layers48
Architecturejais
Smallest quant18.4 GB
Quick answer

Jais Family 30b 16k Chat needs about 39.7 GB of memory at Q4_K_M (a 27.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 21 quants, from 18.4 GB (IQ1_S) to 33.1 GB (Q6_K).

30.8B parameter Jais Family 30b 16k Chat model in GGUF format

The Jais Family 30b 16k Chat model offers 30.8 billion parameters and a 16,384 token context window. It is released under the Apache-2.0 license and supports coding tasks. The model is available in multiple quantized forms for different memory budgets.

Good at

  • Large context handling
  • Coding assistance
  • Apache-2.0 licensed

Limits

  • No vision support
  • Requires high VRAM for full precision
  • Large file sizes

Best for

  • Developers needing long context
  • Code generation tasks
  • Fine‑tuning with limited GPU memory

Who it’s for. Engineers and researchers who need a large‑parameter language model with a 16k token context. The model is suitable for applications that require extensive text generation and coding support.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S18.4 GB 30.2 GB
Too big Get file →
IQ1_M18.9 GB 30.7 GB
Too big Get file →
IQ2_XXS19.7 GB 31.5 GB
Too big Get file →
IQ2_XS20.4 GB 32.2 GB
Too big Get file →
IQ2_S20.9 GB 32.6 GB
Too big Get file →
Q2_K_S21.4 GB 33.2 GB
Too big Get file →
IQ2_M21.5 GB 33.3 GB
Too big Get file →
Q2_K21.7 GB 33.5 GB
Too big Get file →
IQ3_XXS22.8 GB 34.6 GB
Too big Get file →
IQ3_XS23.4 GB 35.1 GB
Too big Get file →
IQ3_S23.8 GB 35.6 GB
Too big Get file →
Q3_K_S23.8 GB 35.6 GB
Too big Get file →
IQ3_M25.1 GB 36.9 GB
Too big Get file →
Q3_K_M25.1 GB 36.9 GB
Too big Get file →
Q3_K_L25.4 GB 37.2 GB
Too big Get file →
IQ4_XS26.2 GB 38.0 GB
Too big Get file →
Q4_K_S27.0 GB 38.7 GB
Too big Get file →
Q4_K_M27.9 GB 39.7 GB
Too big Get file →
Q5_K_S29.9 GB 41.7 GB
Too big Get file →
Q5_K_M30.9 GB 42.7 GB
Too big Get file →
Q6_K33.1 GB 44.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (18.45 GB file, 30.2 GB memory at 8k context). For 12 GB VRAM, IQ1_M (18.93 GB file, 30.7 GB memory). For 16 GB VRAM, IQ2_XS (20.45 GB file, 32.2 GB memory).

What GPU do you need for Jais Family 30b 16k 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: 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: the best quant that fits is IQ2_XXS (19.7 GB file, about 31.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (33.1 GB file, about 44.8 GB in use).

Which Jais Family 30b 16k Chat quant should you choose?

Q4_K_M is the usual starting point for Jais Family 30b 16k Chat: it balances file size and quality well. Here it is a 27.9 GB file.

If memory is tight, the smallest file is IQ1_S at 18.4 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
Parameters30.8B
Layers48
Trained context16,384 tokens
KV cache (fp16)1344 KB per token

Source

Quantized bymradermacher
FamilyJais
Licenseapache-2.0
Downloads (HF)853
Last updated2025-03-05

Frequently asked questions about Jais Family 30b 16k Chat

How much VRAM does Jais Family 30b 16k Chat need?

About 39.7 GB at Q4_K_M with an 8K context window. That is the 27.9 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 Family 30b 16k Chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 30.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Jais Family 30b 16k Chat GGUF?

It depends on the quant: IQ1_S is 18.4 GB, IQ1_M is 18.9 GB, IQ2_XXS is 19.7 GB, IQ2_XS is 20.4 GB, IQ2_S is 20.9 GB, Q2_K_S is 21.4 GB and 15 more.

What context length does Jais Family 30b 16k Chat support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 11.3 GB at 8K and 22.5 GB at 16K.

Where can I download Jais Family 30b 16k Chat GGUF?

The files are on Hugging Face in the mradermacher/jais-family-30b-16k-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 30b 16k 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 this model on 8 GB VRAM?

Use the IQ1_S quant, which requires about 30.2 GB memory at 8k context. 8 GB VRAM is insufficient for full inference.

Does this model support vision tasks?

No, the model 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-30b-16k-chat

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Jais models

All Jais →

Other medium models

All medium models →