SA

saiga 70b

SaigaGGUF by FinancialSupportUpdated 2024-02-07
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant39.2 GB
Quick answer

saiga 70b needs about 42.4 GB of memory at its main file (a 39.2 GB file) with an 8K context window, so it fits on a 48 GB GPU.

saiga 70b is a 69B-parameter Saiga model in GGUF format, quantized by FinancialSupport. Its trained context length is 4K tokens. The repository has 1 quant file, from 39.2 GB to 39.2 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—39.2 GB 41.1 GB
Too big Get file →

What GPU do you need for saiga 70b?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is the main file (39.2 GB file, about 42.4 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byFinancialSupport
FamilySaiga
Licenseapache-2.0
Downloads (HF)9
Last updated2024-02-07

Frequently asked questions about saiga 70b

How much VRAM does saiga 70b need?

About 42.4 GB at its main file with an 8K context window. That is the 39.2 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 saiga 70b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 42.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of saiga 70b GGUF?

It depends on the quant: file is 39.2 GB.

What context length does saiga 70b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download saiga 70b GGUF?

The files are on Hugging Face in the FinancialSupport/saiga-70b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does saiga 70b use?

Hugging Face lists the license as apache-2.0. 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 FinancialSupport

All by FinancialSupport →

More Saiga models

All Saiga →

Other large models

All large models →