ST

stairolz 70b

StairolzGGUF by uncensorieUpdated 2023-11-09
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant39.1 GB
Quick answer

stairolz 70b needs about 42.3 GB of memory at Q4_K_S (a 39.1 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 39.1 GB (Q4_K_S) to 48.8 GB (Q5_K_M).

stairolz 70b is a 69B-parameter Stairolz model in GGUF format, quantized by uncensorie. Its trained context length is 4K tokens. The repository has 2 quant files, from 39.1 GB (Q4_K_S) to 48.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S39.1 GB 40.9 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →

What GPU do you need for stairolz 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 Q4_K_S (39.1 GB file, about 42.3 GB in use).

Which stairolz 70b quant should you choose?

Q4_K_S (39.1 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byuncensorie
FamilyStairolz
Licensellama2
Downloads (HF)16
Last updated2023-11-09

Frequently asked questions about stairolz 70b

How much VRAM does stairolz 70b need?

About 42.3 GB at Q4_K_S with an 8K context window. That is the 39.1 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 stairolz 70b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 42.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of stairolz 70b GGUF?

It depends on the quant: Q4_K_S is 39.1 GB, Q5_K_M is 48.8 GB.

What context length does stairolz 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 stairolz 70b GGUF?

The files are on Hugging Face in the uncensorie/stairolz-70b-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 stairolz 70b 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 uncensorie

All by uncensorie →

More Stairolz models

All Stairolz →

Other large models

All large models →