Llama 2 new GGUFFF needs about 5.1 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU.
Llama 2 new GGUFFF is a 6.74B-parameter Llama model in GGUF format, quantized by Gargaz. Its trained context length is 16K tokens. The repository has 1 quant file, from 4.1 GB (Q4_K_M) to 4.1 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 4.1 GB | 5.1 GB | Fits | Get file → |
What GPU do you need for Llama 2 new GGUFFF?
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: the best quant that fits is Q4_K_M (4.1 GB file, about 5.1 GB in use).
Which Llama 2 new GGUFFF quant should you choose?
Q4_K_M is the usual starting point for Llama 2 new GGUFFF: it balances file size and quality well. Here it is a 4.1 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama 2 new GGUFFF
How much VRAM does Llama 2 new GGUFFF need?
About 5.1 GB at Q4_K_M with an 8K context window. That is the 4.1 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 new GGUFFF on an 8 GB GPU?
Yes, with Q4_K_M: the 4.1 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llama 2 new GGUFFF GGUF?
It depends on the quant: Q4_K_M is 4.1 GB.
What context length does Llama 2 new GGUFFF support?
The GGUF header lists a trained context length of 16,384 tokens (16K).
Where can I download Llama 2 new GGUFFF GGUF?
The files are on Hugging Face in the Gargaz/Llama-2-new-GGUFFF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.