Jais 2 70B Chat needs about 50.8 GB of memory at Q4_K_M (a 44.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 9 quants, from 27.8 GB (Q2_K) to 144.1 GB (BF16).
Jais 2 70B Chat is a 72B-parameter Jais model in GGUF format, quantized by inception42. Its trained context length is 8K tokens. The repository has 9 quant files, from 27.8 GB (Q2_K) to 144.1 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 27.8 GB | 31.6 GB | Too big | Get file → | |
| Q3_K_M | 36.3 GB | 41.1 GB | Too big | Get file → | |
| Q4_0 | 40.8 GB | 46.2 GB | Too big | Get file → | |
| Q4_K_M | 44.9 GB | 50.8 GB | Too big | Get file → | |
| Q5_0 | 49.7 GB | 56.2 GB | Too big | Get file → | |
| Q5_K_M | 51.8 GB | 58.5 GB | Too big | Get file → | |
| Q6_K | 59.1 GB | 66.7 GB | Too big | Get file → | |
| Q8_0 | 76.6 GB | 86.3 GB | Too big | Get file → | |
| BF16 | 144.1 GB | 161.9 GB | Too big | Get file → |
What GPU do you need for Jais 2 70B Chat?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q2_K (27.8 GB file, about 31.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_0 (40.8 GB file, about 46.2 GB in use).
Which Jais 2 70B Chat quant should you choose?
Q4_K_M is the usual starting point for Jais 2 70B Chat: it balances file size and quality well. Here it is a 44.9 GB file.
The Q8_0 file is 76.6 GB, about 1.7 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 27.8 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 2 70B Chat
How much VRAM does Jais 2 70B Chat need?
About 50.8 GB at Q4_K_M with an 8K context window. That is the 44.9 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 2 70B Chat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 31.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Jais 2 70B Chat GGUF?
It depends on the quant: Q2_K is 27.8 GB, Q3_K_M is 36.3 GB, Q4_0 is 40.8 GB, Q4_K_M is 44.9 GB, Q5_0 is 49.7 GB, Q5_K_M is 51.8 GB and 3 more.
What context length does Jais 2 70B Chat support?
The GGUF header lists a trained context length of 8,192 tokens (8K).
Where can I download Jais 2 70B Chat GGUF?
The files are on Hugging Face in the inception42/Jais-2-70B-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 2 70B 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.