llama 3 70b quantised needs about 51.8 GB of memory at Q5_K_S (a 48.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds.
llama 3 70b quantised is a 70.6B-parameter Llama model in GGUF format, quantized by farhan-ahmad. Its trained context length is 8K tokens. The repository has 1 quant file, from 48.7 GB (Q5_K_S) to 48.7 GB (Q5_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_S | 48.7 GB | 51.8 GB | Too big | Get file → |
What GPU do you need for llama 3 70b quantised?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which llama 3 70b quantised quant should you choose?
Q5_K_S (48.7 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about llama 3 70b quantised
How much VRAM does llama 3 70b quantised need?
About 51.8 GB at Q5_K_S with an 8K context window. That is the 48.7 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 70b quantised on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 51.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of llama 3 70b quantised GGUF?
It depends on the quant: Q5_K_S is 48.7 GB.
What context length does llama 3 70b quantised support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.
Where can I download llama 3 70b quantised GGUF?
The files are on Hugging Face in the farhan-ahmad/llama-3-70b-quantised repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does llama 3 70b quantised use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.