LL

NousResearch Meta Llama 3.1 8B Instruct

LlamaGGUF by RichardErkhovUpdated 2024-08-05
Download on Hugging Face
Parameters8B
Context—
Layers—
Architecture—
Smallest quant0.0 GB
Quick answer

NousResearch Meta Llama 3.1 8B Instruct needs about 0.5 GB of memory at Q4_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.0 GB (IQ4_NL) to 7.9 GB (Q8_0).

NousResearch Meta Llama 3.1 8B Instruct is a 8B-parameter Llama model in GGUF format, quantized by RichardErkhov. The repository has 22 quant files, from 0.0 GB (IQ3_M) to 7.9 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL0.0 GB 0.5 GB
Fits Get file →
IQ4_XS0.0 GB 0.5 GB
Fits Get file →
Q3_K0.0 GB 0.5 GB
Fits Get file →
Q3_K_L0.0 GB 0.5 GB
Fits Get file →
Q3_K_M0.0 GB 0.5 GB
Fits Get file →
Q4_00.0 GB 0.5 GB
Fits Get file →
Q4_10.0 GB 0.5 GB
Fits Get file →
Q4_K0.0 GB 0.5 GB
Fits Get file →
Q4_K_M0.0 GB 0.5 GB
Fits Get file →
Q4_K_S0.0 GB 0.5 GB
Fits Get file →
Q5_00.0 GB 0.5 GB
Fits Get file →
IQ3_M0.0 GB 0.5 GB
Fits Get file →
Q3_K_S0.3 GB 0.9 GB
Fits Get file →
Q5_K_S0.7 GB 1.3 GB
Fits Get file →
IQ3_S1.2 GB 1.9 GB
Fits Get file →
IQ3_XS2.6 GB 3.4 GB
Fits Get file →
Q2_K3.2 GB 4.1 GB
Fits Get file →
Q5_K4.9 GB 6.0 GB
Fits Get file →
Q5_K_M5.1 GB 6.3 GB
Fits Get file →
Q6_K6.1 GB 7.3 GB
Tight Get file →
Q5_16.1 GB 7.3 GB
Tight Get file →
Q8_07.9 GB 9.4 GB
Too big Get file →

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

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: the best quant that fits is IQ3_XS (2.6 GB file, about 3.4 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K (4.9 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_1 (6.1 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.9 GB file, about 9.4 GB in use).

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

Q4_K_M is the usual starting point for NousResearch Meta Llama 3.1 8B Instruct: it balances file size and quality well. Here it is a 0.0 GB file.

The Q8_0 file is 7.9 GB, about Infinity times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ4_NL at 0.0 GB, with the quality trade-offs that come with fewer bits. 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

Parameters8B

Source

Quantized byRichardErkhov
FamilyLlama
Downloads (HF)108
Last updated2024-08-05

Frequently asked questions about NousResearch Meta Llama 3.1 8B Instruct

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

About 0.5 GB at Q4_K_M with an 8K context window. That is the 0.0 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 NousResearch Meta Llama 3.1 8B Instruct on an 8 GB GPU?

Yes, with Q5_1: the 6.1 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: IQ4_NL is 0.0 GB, IQ4_XS is 0.0 GB, Q3_K is 0.0 GB, Q3_K_L is 0.0 GB, Q3_K_M is 0.0 GB, Q4_0 is 0.0 GB and 16 more.

Where can I download NousResearch Meta Llama 3.1 8B Instruct GGUF?

The files are on Hugging Face in the RichardErkhov/NousResearch_-_Meta-Llama-3.1-8B-Instruct-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other small models

All small models →