llama3 needs about 2.8 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.
llama3 is a 3.4B-parameter Llama model in GGUF format, quantized by xiagf. The repository has 1 quant file, from 2.1 GB (Q4_K_M) to 2.1 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.1 GB | 2.8 GB | Fits | Get file → |
What GPU do you need for llama3?
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: the best quant that fits is Q4_K_M (2.1 GB file, about 2.8 GB in use).
Which llama3 quant should you choose?
Q4_K_M is the usual starting point for llama3: it balances file size and quality well. Here it is a 2.1 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about llama3
How much VRAM does llama3 need?
About 2.8 GB at Q4_K_M with an 8K context window. That is the 2.1 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 llama3 on an 8 GB GPU?
Yes, with Q4_K_M: the 2.1 GB file needs about 2.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of llama3 GGUF?
It depends on the quant: Q4_K_M is 2.1 GB.
Where can I download llama3 GGUF?
The files are on Hugging Face in the xiagf/llama3 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.