LL

spack llama 7b

LlamaGGUF by daniellnicholsUpdated 2024-01-08
Download on Hugging Face
Parameters6.74B
Context16K
Layers32
Architecturellama
Smallest quant3.8 GB
Quick answer

spack llama 7b needs about 10.3 GB of memory at Q6_K (a 5.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 3.8 GB (Q4_0) to 13.5 GB (F16).

spack llama 7b is a 6.74B-parameter Llama model in GGUF format, quantized by daniellnichols. Its trained context length is 16K tokens. The repository has 4 quant files, from 3.8 GB (Q4_0) to 13.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_03.8 GB 8.6 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →
F1613.5 GB 18.3 GB
Too big Get file →

What GPU do you need for spack llama 7b?

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: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (13.5 GB file, about 18.3 GB in use).

Which spack llama 7b quant should you choose?

Q6_K (5.5 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q4_0 at 3.8 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
Parameters6.74B
Layers32
Trained context16,384 tokens
KV cache (fp16)512 KB per token

Source

Quantized bydaniellnichols
FamilyLlama
Licensellama2
Downloads (HF)35
Last updated2024-01-08

Frequently asked questions about spack llama 7b

How much VRAM does spack llama 7b need?

About 10.3 GB at Q6_K with an 8K context window. That is the 5.5 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 spack llama 7b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of spack llama 7b GGUF?

It depends on the quant: Q4_0 is 3.8 GB, Q6_K is 5.5 GB, Q8_0 is 7.2 GB, F16 is 13.5 GB.

What context length does spack llama 7b support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.3 GB at 8K and 8.6 GB at 16K.

Where can I download spack llama 7b GGUF?

The files are on Hugging Face in the daniellnichols/spack-llama-7b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does spack llama 7b 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 from daniellnichols

All by daniellnichols →

More Llama models

All Llama →

Other small models

All small models →