Jais Adapted 70b needs about 45.0 GB of memory at Q4_K_M (a 41.8 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 22 quants, from 14.8 GB (IQ1_S) to 49.1 GB (Q5_K_M).
Jais Adapted 70b – 69.5B parameter Llama model
Jais Adapted 70b is a 69.5B parameter Llama architecture model trained on 4096 token context. It is released under apache-2.0 and supports coding tasks. The model is available in multiple GGUF quantizations.
Good at
- Coding tasks
- Large context reasoning
- LLM inference
Limits
- No vision support
- Requires 8k context for estimates
- Large memory footprint
Best for
- Code generation
- Technical documentation
- Long-form content creation
Who it’s for. Developers and researchers needing a large language model for code and text generation. The model is suitable for environments where 8k token context is acceptable and sufficient GPU memory is available.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 14.8 GB | 16.6 GB | Too big | Get file → | |
| IQ1_M | 16.2 GB | 18.1 GB | Too big | Get file → | |
| IQ2_XXS | 18.6 GB | 20.4 GB | Too big | Get file → | |
| IQ2_XS | 20.6 GB | 22.4 GB | Too big | Get file → | |
| IQ2_S | 21.6 GB | 23.5 GB | Too big | Get file → | |
| IQ2_M | 23.5 GB | 25.4 GB | Too big | Get file → | |
| Q2_K_S | 23.9 GB | 25.7 GB | Too big | Get file → | |
| Q2_K | 25.8 GB | 27.6 GB | Too big | Get file → | |
| IQ3_XXS | 26.9 GB | 28.7 GB | Too big | Get file → | |
| IQ3_XS | 28.6 GB | 30.5 GB | Too big | Get file → | |
| IQ3_S | 30.2 GB | 32.1 GB | Too big | Get file → | |
| Q3_K_S | 30.2 GB | 32.1 GB | Too big | Get file → | |
| IQ3_M | 31.3 GB | 33.1 GB | Too big | Get file → | |
| Q3_K_M | 33.6 GB | 35.4 GB | Too big | Get file → | |
| Q3_K_L | 36.5 GB | 38.3 GB | Too big | Get file → | |
| IQ4_XS | 37.2 GB | 39.0 GB | Too big | Get file → | |
| Q4_0 | 39.4 GB | 41.2 GB | Too big | Get file → | |
| Q4_K_S | 39.6 GB | 41.5 GB | Too big | Get file → | |
| Q4_K_M | 41.8 GB | 43.6 GB | Too big | Get file → | |
| Q4_1 | 43.5 GB | 45.4 GB | Too big | Get file → | |
| Q5_K_S | 47.9 GB | 49.7 GB | Too big | Get file → | |
| Q5_K_M | 49.1 GB | 51.0 GB | Too big | Get file → |
For 16GB VRAM use IQ1_S (14.8 GB file, 18 GB memory). For 24GB VRAM use Q2_K_S (23.86 GB file, 27 GB memory). For 32GB VRAM use Q4_K_M (41.79 GB file, 45 GB memory). Estimates are approximate.
What GPU do you need for Jais Adapted 70b?
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 IQ2_XS (20.6 GB file, about 23.8 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_XS (28.6 GB file, about 31.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_1 (43.5 GB file, about 46.7 GB in use).
Which Jais Adapted 70b quant should you choose?
Q4_K_M is the usual starting point for Jais Adapted 70b: it balances file size and quality well. Here it is a 41.8 GB file.
If memory is tight, the smallest file is IQ1_S at 14.8 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 Adapted 70b
How much VRAM does Jais Adapted 70b need?
About 45.0 GB at Q4_K_M with an 8K context window. That is the 41.8 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 Adapted 70b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Jais Adapted 70b GGUF?
It depends on the quant: IQ1_S is 14.8 GB, IQ1_M is 16.2 GB, IQ2_XXS is 18.6 GB, IQ2_XS is 20.6 GB, IQ2_S is 21.6 GB, IQ2_M is 23.5 GB and 16 more.
What context length does Jais Adapted 70b support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.
Where can I download Jais Adapted 70b GGUF?
The files are on Hugging Face in the mradermacher/jais-adapted-70b-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 Adapted 70b 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 Adapted 70b on 8GB VRAM?
No, the smallest quant requires 18 GB memory at 8k context, exceeding 8GB VRAM.
What context length does the model support?
The model was trained on 4096 token context and is best used with 8k context for memory estimates.
Is the model licensed for commercial use?
Yes, it is licensed under apache-2.0, allowing commercial use.