Meta Llama3 70B Instruct v2 needs about 61.1 GB of memory at Q6_K (a 57.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds.
Meta Llama3 70B Instruct v2 is a 70.6B-parameter Llama model in GGUF format, quantized by VinayHajare. Its trained context length is 8K tokens. The repository has 1 quant file, from 57.9 GB (Q6_K) to 57.9 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 57.9 GB (2 parts) | 61.1 GB | Too big | Get file → |
What GPU do you need for Meta Llama3 70B Instruct v2?
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 Meta Llama3 70B Instruct v2 quant should you choose?
Q6_K (57.9 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Meta Llama3 70B Instruct v2
How much VRAM does Meta Llama3 70B Instruct v2 need?
About 61.1 GB at Q6_K with an 8K context window. That is the 57.9 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 Meta Llama3 70B Instruct v2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 61.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Meta Llama3 70B Instruct v2 GGUF?
It depends on the quant: Q6_K is 57.9 GB.
What context length does Meta Llama3 70B Instruct v2 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 Meta Llama3 70B Instruct v2 GGUF?
The files are on Hugging Face in the VinayHajare/Meta-Llama3-70B-Instruct-v2-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 Meta Llama3 70B Instruct v2 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.