LL

Meta Llama 3.1 8B Instruct

LlamaGGUF by GPT4All-CommunityUpdated 2024-08-12
Download on Hugging Face
Parameters8B
Context128K
Layers32
Architecturellama
Smallest quant4.7 GB
Quick answer

Meta Llama 3.1 8B Instruct needs about 6.2 GB of memory at Q4_0 (a 4.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 4.7 GB (Q4_0) to 16.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Meta Llama 3.1 8B Instruct with 128k context

Meta Llama 3.1 8B Instruct is a 8B parameter model converted to GGUF. It supports a 131072 token context length and is available in Q4_0 and F16 quantizations. The model is licensed under llama3.1.

Good at

  • Large context handling
  • Instruction following
  • Open-source compatibility

Limits

  • No vision support
  • Requires GPT4All v3.1.1
  • License is llama3.1

Best for

  • Long-form content generation
  • Complex instruction tasks
  • Research prototyping

Who it’s for. Developers and researchers needing a large-context LLM in a lightweight GGUF format. Suitable for local deployment with sufficient RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_04.7 GB 6.2 GB
Fits Get file →
F1616.1 GB 17.6 GB
Too big Get file →

For 8 GB VRAM, use the Q4_0 quantization (file size 4.66 GB, estimated memory 6.2 GB at 8 k context). For higher precision and more RAM, the F16 quantization (16.07 GB, 17.6 GB memory) is available.

What GPU do you need for Meta Llama 3.1 8B Instruct?

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: the best quant that fits is Q4_0 (4.7 GB file, about 6.2 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_0 (4.7 GB file, about 6.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_0 (4.7 GB file, about 6.2 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

Which Meta Llama 3.1 8B Instruct quant should you choose?

Q4_0 (4.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byGPT4All-Community
FamilyLlama
Licensellama3.1
Downloads (HF)1,283
Last updated2024-08-12

Frequently asked questions about Meta Llama 3.1 8B Instruct

How much VRAM does Meta Llama 3.1 8B Instruct need?

About 6.2 GB at Q4_0 with an 8K context window. That is the 4.7 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 Meta Llama 3.1 8B Instruct on an 8 GB GPU?

Yes, with Q4_0: the 4.7 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Meta Llama 3.1 8B Instruct GGUF?

It depends on the quant: Q4_0 is 4.7 GB, F16 is 16.1 GB.

What context length does Meta Llama 3.1 8B Instruct support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Meta Llama 3.1 8B Instruct GGUF?

The files are on Hugging Face in the GPT4All-Community/Meta-Llama-3.1-8B-Instruct-128k-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 3.1 8B Instruct use?

Hugging Face lists the license as llama3.1. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the Q4_0 quantization requires about 6.2 GB of memory at 8 k context, fitting within 8 GB VRAM.

What context length does this model support?

It supports a 131072 token context length, as indicated by the "llama.context_length" setting.

Is this model open-source?

Yes, it is licensed under llama3.1 and available via the GPT4All community repository.

Other GGUFs of Llama-3.1-8B-Instruct

Similar models

Browse all →

More from GPT4All-Community

All by GPT4All-Community →

More Llama models

All Llama →

Other small models

All small models →