TI

TinyLLama v0

TinyllamaGGUF by aladarUpdated 2023-10-18
Download on Hugging Face
Parameters5M
Context2K
Layers8
Architecturellama
Smallest quant0.0 GB
Quick answer

TinyLLama v0 needs about 0.5 GB of memory at F16 (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.0 GB (Q8_0) to 0.0 GB (F32).

TinyLLama v0 is a 5M-parameter Tinyllama model in GGUF format, quantized by aladar. Its trained context length is 2K tokens. The repository has 3 quant files, from 0.0 GB (Q8_0) to 0.0 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.0 GB 0.5 GB
Fits Get file →
F160.0 GB 0.5 GB
Fits Get file →
F320.0 GB 0.5 GB
Fits Get file →

What GPU do you need for TinyLLama v0?

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 F32 (0.0 GB file, about 0.5 GB in use).

Which TinyLLama v0 quant should you choose?

F16 (0.0 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 Q8_0 at 0.0 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters5M
Layers8
Trained context2,048 tokens
KV cache (fp16)2 KB per token

Source

Quantized byaladar
FamilyTinyllama
Licensemit
Downloads (HF)199
Last updated2023-10-18

Frequently asked questions about TinyLLama v0

How much VRAM does TinyLLama v0 need?

About 0.5 GB at F16 with an 8K context window. That is the 0.0 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 v0 on an 8 GB GPU?

Yes, with F32: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinyLLama v0 GGUF?

It depends on the quant: Q8_0 is 0.0 GB, F16 is 0.0 GB, F32 is 0.0 GB.

What context length does TinyLLama v0 support?

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

Where can I download TinyLLama v0 GGUF?

The files are on Hugging Face in the aladar/TinyLLama-v0-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 TinyLLama v0 use?

Hugging Face lists the license as mit. 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 aladar

All by aladar →

More Tinyllama models

All Tinyllama →

Other tiny models

All tiny models →