Jallabi 40B needs about 12.9 GB of memory at Q4_K_M (a 11.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 7.1 GB (Q2_K) to 19.9 GB (Q8_0).
Jallabi 40B – 18.8B parameter Llama model in GGUF format
Jallabi 40B is a 18.8B parameter Llama model quantized for GGUF usage. It supports a 4096 token context window and is released under the apache-2.0 license. The model is available in multiple quantization levels for different memory budgets.
Good at
- Large context handling
- Flexible quantization options
- Apache-2.0 licensed
Limits
- No vision support
- Requires at least 8.7 GB VRAM for Q2_K
- No mixture of experts
Best for
- Local inference on mid‑range GPUs
- Fine‑tuning with limited VRAM
- Educational demonstrations
Who it’s for. Developers and researchers who need a sizable Llama model that can run locally with GGUF. The model is suitable for those who prefer open‑source licensing and flexible quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 7.1 GB | 8.1 GB | Too big | Get file → | |
| IQ3_XS | 7.9 GB | 8.9 GB | Too big | Get file → | |
| Q3_K_S | 8.2 GB | 9.3 GB | Too big | Get file → | |
| IQ3_S | 8.3 GB | 9.3 GB | Too big | Get file → | |
| IQ3_M | 8.6 GB | 9.6 GB | Too big | Get file → | |
| Q3_K_M | 9.2 GB | 10.2 GB | Too big | Get file → | |
| Q3_K_L | 9.9 GB | 11.0 GB | Too big | Get file → | |
| IQ4_XS | 10.2 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_S | 10.8 GB | 11.8 GB | Too big | Get file → | |
| Q4_K_M | 11.3 GB | 12.4 GB | Too big | Get file → | |
| Q5_K_S | 13.0 GB | 14.0 GB | Too big | Get file → | |
| Q5_K_M | 13.3 GB | 14.3 GB | Too big | Get file → | |
| Q6_K | 15.4 GB | 16.4 GB | Too big | Get file → | |
| Q8_0 | 19.9 GB | 21.0 GB | Too big | Get file → |
For 8–12 GB VRAM, use Q2_K (8.7 GB) or Q3_K_S (9.8 GB). For 12–15 GB VRAM, Q4_K_M (12.9 GB) or Q5_K_S (14.5 GB) are good choices. For 16 GB or more, Q6_K (17 GB) or Q8_0 (21.5 GB) provide higher quality.
What GPU do you need for Jallabi 40B?
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 IQ4_XS (10.2 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (13.3 GB file, about 14.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (19.9 GB file, about 21.5 GB in use).
Which Jallabi 40B quant should you choose?
Q4_K_M is the usual starting point for Jallabi 40B: it balances file size and quality well. Here it is a 11.3 GB file.
The Q8_0 file is 19.9 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.
If memory is tight, the smallest file is Q2_K at 7.1 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 Jallabi 40B
How much VRAM does Jallabi 40B need?
About 12.9 GB at Q4_K_M with an 8K context window. That is the 11.3 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 Jallabi 40B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Jallabi 40B GGUF?
It depends on the quant: Q2_K is 7.1 GB, IQ3_XS is 7.9 GB, Q3_K_S is 8.2 GB, IQ3_S is 8.3 GB, IQ3_M is 8.6 GB, Q3_K_M is 9.2 GB and 8 more.
What context length does Jallabi 40B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.
Where can I download Jallabi 40B GGUF?
The files are on Hugging Face in the mradermacher/llama3-Jallabi-40B-s-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 Jallabi 40B 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 Jallabi 40B on 8 GB VRAM?
The smallest quant, Q2_K, requires 8.7 GB VRAM, so 8 GB is insufficient.
Does this model support vision tasks?
No, the model has no vision capabilities.
What license applies to Jallabi 40B?
The model is released under the apache-2.0 license.