LL

SillyTilly Meta Llama 3.1 8B

LlamaGGUF by RichardErkhovUpdated 2024-08-05
Download on Hugging Face
Parameters8.03B
Context128K
Layers—
Architecturellama
Smallest quant0.6 GB
Quick answer

SillyTilly Meta Llama 3.1 8B needs about 4.6 GB of memory at IQ3_S (a 3.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 0.6 GB (Q4_0) to 4.5 GB (IQ4_XS).

SillyTilly Meta Llama 3.1 8B is a 8.03B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 128K tokens. The repository has 10 quant files, from 0.6 GB (Q4_0) to 4.5 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.6 GB 1.2 GB
Fits Get file →
Q2_K3.2 GB 4.1 GB
Fits Get file →
IQ3_XS3.5 GB 4.4 GB
Fits Get file →
Q3_K_S3.7 GB 4.6 GB
Fits Get file →
IQ3_S3.7 GB 4.6 GB
Fits Get file →
IQ3_M3.8 GB 4.7 GB
Fits Get file →
Q3_K4.0 GB 5.0 GB
Fits Get file →
Q3_K_M4.0 GB 5.0 GB
Fits Get file →
Q3_K_L4.3 GB 5.3 GB
Fits Get file →
IQ4_XS4.5 GB 5.5 GB
Fits Get file →

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

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 Q4_0 (0.6 GB file, about 1.2 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.5 GB file, about 5.5 GB in use).

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

IQ3_S (3.7 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is Q4_0 at 0.6 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

Architecturellama
Parameters8.03B
Trained context131,072 tokens

Source

Quantized byRichardErkhov
FamilyLlama
Downloads (HF)27
Last updated2024-08-05

Frequently asked questions about SillyTilly Meta Llama 3.1 8B

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

About 4.6 GB at IQ3_S with an 8K context window. That is the 3.7 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 SillyTilly Meta Llama 3.1 8B on an 8 GB GPU?

Yes, with IQ4_XS: the 4.5 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: Q4_0 is 0.6 GB, Q2_K is 3.2 GB, IQ3_XS is 3.5 GB, Q3_K_S is 3.7 GB, IQ3_S is 3.7 GB, IQ3_M is 3.8 GB and 4 more.

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

The GGUF header lists a trained context length of 131,072 tokens (128K).

Where can I download SillyTilly Meta Llama 3.1 8B GGUF?

The files are on Hugging Face in the RichardErkhov/SillyTilly_-_Meta-Llama-3.1-8B-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 →