llama3 8b instruct 32k needs about 6.4 GB of memory at its main file (a 4.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 9 quants, from 2.7 GB to 16.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
llama3 8b instruct 32k is a 8.03B-parameter Llama model in GGUF format, quantized by nisten. Its trained context length is 32K tokens. The repository has 9 quant files, from 2.7 GB to 16.1 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.7 GB | 4.3 GB | Fits | Get file → | |
| — | 3.3 GB | 4.9 GB | Fits | Get file → | |
| — | 4.1 GB | 5.7 GB | Fits | Get file → | |
| — | 4.2 GB | 5.8 GB | Fits | Get file → | |
| — | 4.8 GB | 6.4 GB | Fits | Get file → | |
| — | 6.1 GB | 7.6 GB | Tight | Get file → | |
| — | 6.9 GB | 8.4 GB | Too big | Get file → | |
| — | 8.5 GB | 10.1 GB | Too big | Get file → | |
| F16 | 16.1 GB | 17.6 GB | Too big | Get file → |
What GPU do you need for llama3 8b instruct 32k?
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: the best quant that fits is the main file (4.2 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (6.1 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (8.5 GB file, about 10.1 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (8.5 GB file, about 10.1 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).
Which llama3 8b instruct 32k quant should you choose?
If memory is tight, the smallest file is the first one in the table at 2.7 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about llama3 8b instruct 32k
How much VRAM does llama3 8b instruct 32k need?
About 6.4 GB at its main file with an 8K context window. That is the 4.8 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 8b instruct 32k on an 8 GB GPU?
Yes, with the smaller files: the 6.1 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of llama3 8b instruct 32k GGUF?
It depends on the quant: file is 2.7 GB, file is 3.3 GB, file is 4.1 GB, file is 4.2 GB, file is 4.8 GB, file is 6.1 GB and 3 more.
What context length does llama3 8b instruct 32k support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download llama3 8b instruct 32k GGUF?
The files are on Hugging Face in the nisten/llama3-8b-instruct-32k-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 8b instruct 32k 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.