Llama 2 7b Chat Hf needs about 18.3 GB of memory at BF16 (a 13.5 GB file) with an 8K context window, so it fits on a 24 GB GPU.
Llama 2 7b Chat Hf is a 6.74B-parameter Llama model in GGUF format, quantized by teleprint-me. Its trained context length is 4K tokens. The repository has 1 quant file, from 13.5 GB (BF16) to 13.5 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 13.5 GB | 16.1 GB | Too big | Get file → |
What GPU do you need for Llama 2 7b Chat Hf?
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 BF16 (13.5 GB file, about 18.3 GB in use).
Which Llama 2 7b Chat Hf quant should you choose?
BF16 (13.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama 2 7b Chat Hf
How much VRAM does Llama 2 7b Chat Hf need?
About 18.3 GB at BF16 with an 8K context window. That is the 13.5 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 7b Chat Hf on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama 2 7b Chat Hf GGUF?
It depends on the quant: BF16 is 13.5 GB.
What context length does Llama 2 7b Chat Hf support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.
Where can I download Llama 2 7b Chat Hf GGUF?
The files are on Hugging Face in the teleprint-me/llama-2-7b-chat 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 7b Chat Hf use?
Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.