llama 3 instruct 8b needs about 18.7 GB of memory at F16 (a 17.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 8.5 GB (Q8_0) to 32.1 GB (F32).
llama 3 instruct 8b is a 8.03B-parameter Llama model in GGUF format, quantized by xaskasdf. Its trained context length is 8K tokens. The repository has 3 quant files, from 8.5 GB (Q8_0) to 32.1 GB (F32).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 8.5 GB | 10.1 GB | Too big | Get file → | |
| F16 | 17.1 GB | 18.7 GB | Too big | Get file → | |
| F32 | 32.1 GB | 33.7 GB | Too big | Get file → |
What GPU do you need for llama 3 instruct 8b?
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: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (17.1 GB file, about 18.7 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (17.1 GB file, about 18.7 GB in use).
- 48 GB VRAM: the best quant that fits is F32 (32.1 GB file, about 33.7 GB in use).
Which llama 3 instruct 8b quant should you choose?
F16 (17.1 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.
If memory is tight, the smallest file is Q8_0 at 8.5 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about llama 3 instruct 8b
How much VRAM does llama 3 instruct 8b need?
About 18.7 GB at F16 with an 8K context window. That is the 17.1 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 3 instruct 8b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of llama 3 instruct 8b GGUF?
It depends on the quant: Q8_0 is 8.5 GB, F16 is 17.1 GB, F32 is 32.1 GB.
What context length does llama 3 instruct 8b support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.
Where can I download llama 3 instruct 8b GGUF?
The files are on Hugging Face in the xaskasdf/llama-3-instruct-8b-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.