TI

tinyllamas stories

TinyllamasGGUF by klosaxUpdated 2023-08-22
Download on Hugging Face
Parameters134M
Context1K
Layers—
Architecturellama
Smallest quant0.0 GB
Quick answer

tinyllamas stories needs about 0.6 GB of memory at F32 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.0 GB (F32) to 0.5 GB (F32).

tinyllamas stories is a 134M-parameter Tinyllamas model in GGUF format, quantized by klosax. Its trained context length is 1K tokens. The repository has 4 quant files, from 0.0 GB (F32) to 0.5 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F320.0 GB 0.5 GB
Fits Get file →
F320.1 GB 0.6 GB
Fits Get file →
F320.2 GB 0.7 GB
Fits Get file →
F320.5 GB 1.0 GB
Fits Get file →

What GPU do you need for tinyllamas stories?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is F32 (0.5 GB file, about 1.1 GB in use).

Which tinyllamas stories quant should you choose?

F32 (0.1 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.

If memory is tight, the smallest file is F32 at 0.0 GB, with the quality trade-offs that come with fewer bits. 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
Parameters134M
Trained context1,024 tokens

Source

Quantized byklosax
Downloads (HF)776
Last updated2023-08-22

Frequently asked questions about tinyllamas stories

How much VRAM does tinyllamas stories need?

About 0.6 GB at F32 with an 8K context window. That is the 0.1 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 tinyllamas stories on an 8 GB GPU?

Yes, with F32: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of tinyllamas stories GGUF?

It depends on the quant: F32 is 0.0 GB, F32 is 0.1 GB, F32 is 0.2 GB, F32 is 0.5 GB.

What context length does tinyllamas stories support?

The GGUF header lists a trained context length of 1,024 tokens (1K).

Where can I download tinyllamas stories GGUF?

The files are on Hugging Face in the klosax/tinyllamas-stories-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from klosax

All by klosax →

More Tinyllamas models

All Tinyllamas →

Other tiny models

All tiny models →