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 10 quants, from 21.7 GB (Q2_K) to 33.1 GB (Q6_K).
Jais Family 30b 16k Chat is a 30.8B-parameter Jais model in GGUF format, quantized by mradermacher. Its trained context length is 16K tokens. The repository has 10 quant files, from 21.7 GB (Q2_K) to 33.1 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 21.7 GB | 33.5 GB | Too big | Get file → | |
| Q3_K_S | 23.8 GB | 35.6 GB | Too big | Get file → | |
| Q3_K_M | 25.1 GB | 36.9 GB | Too big | Get file → | |
| Q3_K_L | 25.4 GB | 37.2 GB | Too big | Get file → | |
| IQ4_XS | 26.2 GB | 38.0 GB | Too big | Get file → | |
| Q4_K_S | 27.0 GB | 38.7 GB | Too big | Get file → | |
| Q4_K_M | 27.9 GB | 39.7 GB | Too big | Get file → | |
| Q5_K_S | 29.9 GB | 41.7 GB | Too big | Get file → | |
| Q5_K_M | 30.9 GB | 42.7 GB | Too big | Get file → | |
| Q6_K | 33.1 GB | 44.8 GB | Too big | Get file → |
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: no quant fits at an 8K context.
- 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 Q2_K at 21.7 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
Source
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 33.5 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: Q2_K is 21.7 GB, Q3_K_S is 23.8 GB, Q3_K_M is 25.1 GB, Q3_K_L is 25.4 GB, IQ4_XS is 26.2 GB, Q4_K_S is 27.0 GB and 4 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-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.