LL

llama quant models

LlamaGGUF by amd-sharkUpdated 2024-09-20
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant13.5 GB
Quick answer

llama quant models needs about 18.3 GB of memory at F16 (a 13.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 13.5 GB (F16) to 16.1 GB (F16).

llama quant models is a 6.74B-parameter Llama model in GGUF format, quantized by amd-shark. Its trained context length is 4K tokens. The repository has 2 quant files, from 13.5 GB (F16) to 16.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1613.5 GB 16.1 GB
Too big Get file →
F1616.1 GB 18.7 GB
Too big Get file →

What GPU do you need for llama quant models?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 20.9 GB in use).

Which llama quant models quant should you choose?

F16 (13.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byamd-shark
FamilyLlama
Licensellama2
Downloads (HF)62
Last updated2024-09-20

Frequently asked questions about llama quant models

How much VRAM does llama quant models need?

About 18.3 GB at F16 with an 8K context window. That is the 13.5 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 llama quant models on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llama quant models GGUF?

It depends on the quant: F16 is 13.5 GB, F16 is 16.1 GB.

What context length does llama quant models support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download llama quant models GGUF?

The files are on Hugging Face in the amd-shark/llama-quant-models 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 quant models use?

Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More Llama models

All Llama →

Other small models

All small models →