LL

Meta Llama 3 12B Instruct Q6 K

LlamaGGUF by win10Updated 2024-05-28
Download on Hugging Face
Parameters11.5B
Context8K
Layers—
Architecturellama
Smallest quant9.5 GB
Quick answer

Meta Llama 3 12B Instruct Q6 K needs about 11.1 GB of memory at Q6_K (a 9.5 GB file) with an 8K context window, so it fits on a 12 GB GPU.

Meta Llama 3 12B Instruct Q6 K is a 11.5B-parameter Llama model in GGUF format, quantized by win10. Its trained context length is 8K tokens. The repository has 1 quant file, from 9.5 GB (Q6_K) to 9.5 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K9.5 GB 11.1 GB
Too big Get file →

What GPU do you need for Meta Llama 3 12B Instruct Q6 K?

These figures add the file size, an fp16 KV cache at an 8K context window 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 Q6_K (9.5 GB file, about 11.1 GB in use).

Which Meta Llama 3 12B Instruct Q6 K quant should you choose?

Q6_K (9.5 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

Architecturellama
Parameters11.5B
Trained context8,192 tokens

Source

Quantized bywin10
FamilyLlama
Licenseother
Downloads (HF)18
Last updated2024-05-28

Frequently asked questions about Meta Llama 3 12B Instruct Q6 K

How much VRAM does Meta Llama 3 12B Instruct Q6 K need?

About 11.1 GB at Q6_K with an 8K context window. That is the 9.5 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 Llama 3 12B Instruct Q6 K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Meta Llama 3 12B Instruct Q6 K GGUF?

It depends on the quant: Q6_K is 9.5 GB.

What context length does Meta Llama 3 12B Instruct Q6 K support?

The GGUF header lists a trained context length of 8,192 tokens (8K).

Where can I download Meta Llama 3 12B Instruct Q6 K GGUF?

The files are on Hugging Face in the win10/Meta-Llama-3-12B-Instruct-Q6_K-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 Llama 3 12B Instruct Q6 K use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Meta-Llama-3-8B-Instruct

Similar models

Browse all →

More from win10

All by win10 →

More Llama models

All Llama →

Other medium models

All medium models →