LL

Llama-3SOME-8B-v2

LlamaGGUF by NikolayKozloffUpdated 2024-06-21
Download on Hugging Face
Parameters8.03B
Context10K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

Llama-3SOME-8B-v2 needs about 6.0 GB of memory at IQ4_XS (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU.

Llama-3SOME-8B-v2 is a 8.03B-parameter Llama model in GGUF format, quantized by NikolayKozloff. Its trained context length is 10K tokens. The repository has 1 quant file, from 4.4 GB (IQ4_XS) to 4.4 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS4.4 GB 6.0 GB
Fits Get file →

What GPU do you need for Llama-3SOME-8B-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: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 GB in use).

Which Llama-3SOME-8B-v2 quant should you choose?

IQ4_XS (4.4 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
Parameters8.03B
Layers32
Trained context10,240 tokens
KV cache (fp16)128 KB per token

Source

Quantized byNikolayKozloff
FamilyLlama
Downloads (HF)6
Last updated2024-06-21

Frequently asked questions about Llama-3SOME-8B-v2

How much VRAM does Llama-3SOME-8B-v2 need?

About 6.0 GB at IQ4_XS with an 8K context window. That is the 4.4 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 Llama-3SOME-8B-v2 on an 8 GB GPU?

Yes, with IQ4_XS: the 4.4 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama-3SOME-8B-v2 GGUF?

It depends on the quant: IQ4_XS is 4.4 GB.

What context length does Llama-3SOME-8B-v2 support?

The GGUF header lists a trained context length of 10,240 tokens (10K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.3 GB at 10K.

Where can I download Llama-3SOME-8B-v2 GGUF?

The files are on Hugging Face in the NikolayKozloff/Llama-3SOME-8B-v2-IQ4_XS-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 Llama-3SOME-8B-v2 use?

Hugging Face lists the license as cc-by-nc-4.0. 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 Llama-3SOME-8B-v2

Similar models

Browse all →

More from NikolayKozloff

All by NikolayKozloff →

More Llama models

All Llama →

Other small models

All small models →