Jais-3-MoVA-36B-A4B needs about 24.5 GB of memory at Q4_K_M (a 22.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.3 GB to 30.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
36B Mixture‑of‑Experts LLM with 4B active params and 512K context
Jais‑3‑MoVA‑36B‑A4B is a sparse Mixture‑of‑Experts model built on the k2‑horizon architecture. It stores 36 billion parameters but activates only 4 billion per token, offering a 512 k context window. The model is licensed under Apache‑2.0.
Good at
- Reasoning
- Large context handling
- Sparse expert activation
Limits
- 512K context window only
- Requires high VRAM for full precision
- No vision support
Best for
- Long‑form reasoning tasks
- Complex question answering
- Large‑scale text generation
Who it’s for. Developers and researchers needing a high‑capacity, sparse LLM for reasoning tasks. The model is suitable for environments that can accommodate its memory demands and support the GGUF format.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.3 GB | 2.4 GB | Fits | Get file → | |
| IQ1_S | 7.9 GB | 10.0 GB | Too big | Get file → | |
| IQ1_M | 8.7 GB | 10.8 GB | Too big | Get file → | |
| IQ2_XXS | 10.1 GB | 12.2 GB | Too big | Get file → | |
| IQ2_XS | 11.2 GB | 13.3 GB | Too big | Get file → | |
| IQ2_S | 11.4 GB | 13.5 GB | Too big | Get file → | |
| IQ2_M | 12.5 GB | 14.6 GB | Too big | Get file → | |
| Q2_K_S | 12.8 GB | 14.9 GB | Too big | Get file → | |
| Q2_K | 13.6 GB | 15.7 GB | Too big | Get file → | |
| IQ3_XXS | 14.6 GB | 16.7 GB | Too big | Get file → | |
| IQ3_XS | 15.7 GB | 17.8 GB | Too big | Get file → | |
| Q3_K_S | 16.4 GB | 18.5 GB | Too big | Get file → | |
| IQ3_S | 16.4 GB | 18.5 GB | Too big | Get file → | |
| IQ3_M | 16.5 GB | 18.7 GB | Too big | Get file → | |
| Q3_K_M | 17.7 GB | 19.8 GB | Too big | Get file → | |
| Q3_K_L | 18.8 GB | 21.0 GB | Too big | Get file → | |
| IQ4_XS | 20.1 GB | 22.2 GB | Too big | Get file → | |
| Q4_0 | 21.3 GB | 23.4 GB | Too big | Get file → | |
| Q4_K_S | 21.4 GB | 23.5 GB | Too big | Get file → | |
| Q4_K_M | 22.4 GB | 24.5 GB | Too big | Get file → | |
| Q4_1 | 23.6 GB | 25.7 GB | Too big | Get file → | |
| Q5_K_S | 25.9 GB | 28.0 GB | Too big | Get file → | |
| Q5_K_M | 26.4 GB | 28.6 GB | Too big | Get file → | |
| Q6_K | 30.8 GB | 32.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (7.86 GB, ~10 GB memory at 8k context). For 12 GB VRAM, IQ2_XS (11.18 GB, ~13.3 GB memory). For 16 GB VRAM, Q3_K_S (16.39 GB, ~18.5 GB memory). Memory estimates are approximate.
What GPU do you need for Jais-3-MoVA-36B-A4B?
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 the main file (0.3 GB file, about 2.4 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 2.4 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 2.4 GB in use).
- 12 GB VRAM: the best quant that fits is IQ1_M (8.7 GB file, about 10.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q2_K (13.6 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_S (21.4 GB file, about 23.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (26.4 GB file, about 28.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (30.8 GB file, about 32.9 GB in use).
Which Jais-3-MoVA-36B-A4B quant should you choose?
Q4_K_M is the usual starting point for Jais-3-MoVA-36B-A4B: it balances file size and quality well. Here it is a 22.4 GB file.
If memory is tight, the smallest file is the first one in the table at 0.3 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Jais-3-MoVA-36B-A4B
How much VRAM does Jais-3-MoVA-36B-A4B need?
About 24.5 GB at Q4_K_M with an 8K context window. That is the 22.4 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-MoVA-36B-A4B on an 8 GB GPU?
Yes, with the smaller files: the 0.3 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Jais-3-MoVA-36B-A4B GGUF?
It depends on the quant: file is 0.3 GB, IQ1_S is 7.9 GB, IQ1_M is 8.7 GB, IQ2_XXS is 10.1 GB, IQ2_XS is 11.2 GB, IQ2_S is 11.4 GB and 18 more.
What context length does Jais-3-MoVA-36B-A4B support?
The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download Jais-3-MoVA-36B-A4B GGUF?
The files are on Hugging Face in the mradermacher/Jais-3-MoVA-36B-A4B-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-3-MoVA-36B-A4B 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‑MoVA‑36B‑A4B on 8 GB VRAM?
Use the IQ1_S quant, which is 7.86 GB and requires about 10 GB of VRAM at 8k context.
Does this model support image input?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.