Jais-3-32B needs about 23.7 GB of memory at Q4_K_M (a 21.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 21.1 GB (Q4_K_M) to 69.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Jais‑3‑32B – 34.8B‑parameter decoder‑only model with 512K context
Jais‑3‑32B is a 34.8B‑parameter dense model in the Jais‑3 family. It supports a 512K token context window and is available in multiple GGUF quantizations for llama.cpp. The model is licensed under apache‑2.0.
Good at
- Long‑form text generation
- Complex reasoning tasks
- Large‑scale language modeling
Limits
- Requires high VRAM – 23.7 GB at 8K context for Q4_K_M
- No vision or multimodal support
- Large context window limits some deployment options
Best for
- Research on long‑context language tasks
- Generating extensive documents
- Fine‑tuning on domain‑specific corpora
Who it’s for. Researchers and developers needing a large, dense decoder‑only model with extensive context. Suitable for environments that can accommodate the high memory footprint and support the K2 Horizon architecture in llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 21.1 GB | 23.7 GB | Too big | Get file → | |
| Q5_0 | 24.1 GB | 26.7 GB | Too big | Get file → | |
| Q5_K_M | 24.7 GB | 27.3 GB | Too big | Get file → | |
| Q6_K | 28.5 GB | 31.2 GB | Too big | Get file → | |
| Q8_0 | 37.0 GB | 39.6 GB | Too big | Get file → | |
| BF16 | 69.6 GB | 72.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (21.08 GB file, 23.7 GB memory). For 16 GB VRAM, Q5_0 (24.09 GB file, 26.7 GB memory) or Q5_K_M (24.7 GB file, 27.3 GB memory). For 32 GB VRAM, Q6_K (28.54 GB file, 31.2 GB memory). For 64 GB VRAM, Q8_0 (36.97 GB file, 39.6 GB memory).
What GPU do you need for Jais-3-32B?
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: the best quant that fits is Q4_K_M (21.1 GB file, about 23.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 31.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (37.0 GB file, about 39.6 GB in use).
Which Jais-3-32B quant should you choose?
Q4_K_M is the usual starting point for Jais-3-32B: it balances file size and quality well. Here it is a 21.1 GB file.
The Q8_0 file is 37.0 GB, about 1.8 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
Source
Frequently asked questions about Jais-3-32B
How much VRAM does Jais-3-32B need?
About 23.7 GB at Q4_K_M with an 8K context window. That is the 21.1 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-3-32B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 23.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Jais-3-32B GGUF?
It depends on the quant: Q4_K_M is 21.1 GB, Q5_0 is 24.1 GB, Q5_K_M is 24.7 GB, Q6_K is 28.5 GB, Q8_0 is 37.0 GB, BF16 is 69.6 GB.
What context length does Jais-3-32B support?
The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Jais-3-32B GGUF?
The files are on Hugging Face in the IFM/Jais-3-32B-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-3-32B 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‑3‑32B on 8 GB VRAM?
No, the smallest quant requires 23.7 GB memory at 8K context. 8 GB VRAM is insufficient.
Does Jais‑3‑32B support vision inputs?
No, the model is decoder‑only and has no vision or multimodal capabilities.
What license applies to Jais‑3‑32B?
The model is released under the apache‑2.0 license.