TI

tinyllama

TinyllamaGGUF by rbai86Updated 2024-01-22
Download on Hugging Face
Parameters1.1B
Context2K
Layers22
Architecturellama
Smallest quant0.6 GB
Quick answer

tinyllama needs about 1.4 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.6 GB (Q4_0) to 1.2 GB (Q8_0).

tinyllama is a 1.1B-parameter Tinyllama model in GGUF format, quantized by rbai86. Its trained context length is 2K tokens. The repository has 3 quant files, from 0.6 GB (Q4_0) to 1.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.6 GB 1.2 GB
Fits Get file →
Q4_K_M0.7 GB 1.2 GB
Fits Get file →
Q8_01.2 GB 1.7 GB
Fits Get file →

What GPU do you need for tinyllama?

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: the best quant that fits is Q8_0 (1.2 GB file, about 1.9 GB in use).

Which tinyllama quant should you choose?

Q4_K_M is the usual starting point for tinyllama: it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 1.2 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q4_0 at 0.6 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
Parameters1.1B
Layers22
Trained context2,048 tokens
KV cache (fp16)22 KB per token

Source

Quantized byrbai86
FamilyTinyllama
Downloads (HF)27
Last updated2024-01-22

Frequently asked questions about tinyllama

How much VRAM does tinyllama need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.7 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 tinyllama on an 8 GB GPU?

Yes, with Q8_0: the 1.2 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of tinyllama GGUF?

It depends on the quant: Q4_0 is 0.6 GB, Q4_K_M is 0.7 GB, Q8_0 is 1.2 GB.

What context length does tinyllama support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 2K.

Where can I download tinyllama GGUF?

The files are on Hugging Face in the rbai86/tinyllama-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 Tinyllama models

All Tinyllama →

Other tiny models

All tiny models →