llama3-13.45b-Instruct needs about 10.4 GB of memory at Q4_K_M (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 18 quants, from 4.2 GB (IQ2_XS) to 53.1 GB (F32).
llama3-13.45b-Instruct is a 13.3B-parameter Llama model in GGUF format, quantized by bartowski. Its trained context length is 8K tokens. The repository has 18 quant files, from 4.2 GB (IQ2_XS) to 53.1 GB (F32).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 4.2 GB | 6.5 GB | Fits | Get file → | |
| IQ2_S | 4.4 GB | 6.8 GB | Fits | Get file → | |
| IQ2_M | 4.7 GB | 7.1 GB | Fits | Get file → | |
| Q2_K | 5.1 GB | 7.5 GB | Tight | Get file → | |
| IQ3_XXS | 5.3 GB | 7.7 GB | Tight | Get file → | |
| IQ3_XS | 5.7 GB | 8.0 GB | Too big | Get file → | |
| Q3_K_S | 5.9 GB | 8.3 GB | Too big | Get file → | |
| IQ3_M | 6.1 GB | 8.5 GB | Too big | Get file → | |
| Q3_K_M | 6.5 GB | 8.9 GB | Too big | Get file → | |
| Q3_K_L | 7.1 GB | 9.4 GB | Too big | Get file → | |
| IQ4_XS | 7.2 GB | 9.6 GB | Too big | Get file → | |
| Q4_K_S | 7.7 GB | 10.0 GB | Too big | Get file → | |
| Q4_K_M | 8.1 GB | 10.4 GB | Too big | Get file → | |
| Q5_K_S | 9.2 GB | 11.6 GB | Too big | Get file → | |
| Q5_K_M | 9.4 GB | 11.8 GB | Too big | Get file → | |
| Q6_K | 10.9 GB | 13.3 GB | Too big | Get file → | |
| Q8_0 | 14.1 GB | 16.5 GB | Too big | Get file → | |
| F32 | 53.1 GB (2 parts) | 55.4 GB | Too big | Get file → |
What GPU do you need for llama3-13.45b-Instruct?
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: the best quant that fits is IQ3_XS (5.7 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (9.4 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (10.9 GB file, about 13.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (14.1 GB file, about 16.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (14.1 GB file, about 16.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (14.1 GB file, about 16.5 GB in use).
Which llama3-13.45b-Instruct quant should you choose?
Q4_K_M is the usual starting point for llama3-13.45b-Instruct: it balances file size and quality well. Here it is a 8.1 GB file.
The Q8_0 file is 14.1 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 IQ2_XS at 4.2 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 llama3-13.45b-Instruct
How much VRAM does llama3-13.45b-Instruct need?
About 10.4 GB at Q4_K_M with an 8K context window. That is the 8.1 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 llama3-13.45b-Instruct on an 8 GB GPU?
Yes, with IQ3_XS: the 5.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of llama3-13.45b-Instruct GGUF?
It depends on the quant: IQ2_XS is 4.2 GB, IQ2_S is 4.4 GB, IQ2_M is 4.7 GB, Q2_K is 5.1 GB, IQ3_XXS is 5.3 GB, IQ3_XS is 5.7 GB and 12 more.
What context length does llama3-13.45b-Instruct support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.9 GB at 8K and 1.9 GB at 8K.
Where can I download llama3-13.45b-Instruct GGUF?
The files are on Hugging Face in the bartowski/llama3-13.45b-Instruct-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 llama3-13.45b-Instruct use?
Hugging Face lists the license as llama3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.