Llama 2 13b orca v1 needs about 17.9 GB of memory at Q6_K (a 10.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 7.4 GB (Q4_0) to 25.8 GB (F16).
Llama 2 13b orca v1 is a 13B-parameter Llama model in GGUF format, quantized by hadongz. Its trained context length is 4K tokens. The repository has 5 quant files, from 7.4 GB (Q4_0) to 25.8 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 7.4 GB | 11.2 GB | Too big | Get file → | |
| Q5_K_M | 9.2 GB | 13.1 GB | Too big | Get file → | |
| Q6_K | 10.7 GB | 14.5 GB | Too big | Get file → | |
| Q8_0 | 13.8 GB | 17.7 GB | Too big | Get file → | |
| F16 | 25.8 GB | 29.7 GB | Too big | Get file → |
What GPU do you need for Llama 2 13b orca v1?
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: the best quant that fits is Q4_0 (7.4 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
- 48 GB VRAM: the best quant that fits is F16 (25.8 GB file, about 33.1 GB in use).
Which Llama 2 13b orca v1 quant should you choose?
Q6_K (10.7 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q4_0 at 7.4 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama 2 13b orca v1
How much VRAM does Llama 2 13b orca v1 need?
About 17.9 GB at Q6_K with an 8K context window. That is the 10.7 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 Llama 2 13b orca v1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama 2 13b orca v1 GGUF?
It depends on the quant: Q4_0 is 7.4 GB, Q5_K_M is 9.2 GB, Q6_K is 10.7 GB, Q8_0 is 13.8 GB, F16 is 25.8 GB.
What context length does Llama 2 13b orca v1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.
Where can I download Llama 2 13b orca v1 GGUF?
The files are on Hugging Face in the hadongz/Llama-2-13b-orca-v1-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 Llama 2 13b orca v1 use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.