TI

TinyLlama 1.1B Chat v0.2

TinyllamaGGUF by TrelisUpdated 2023-09-27
Download on Hugging Face
Parameters1.1B
Context2K
Layers22
Architecturellama
Smallest quant0.7 GB
Quick answer

TinyLlama 1.1B Chat v0.2 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 2 quants, from 0.7 GB (Q4_K) to 0.7 GB (Q4_K_M).

TinyLlama 1.1B Chat v0.2 is a 1.1B-parameter Tinyllama model in GGUF format, quantized by Trelis. Its trained context length is 2K tokens. The repository has 2 quant files, from 0.7 GB (Q4_K) to 0.7 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K0.7 GB 1.2 GB
Fits Get file →
Q4_K_M0.7 GB 1.2 GB
Fits Get file →

What GPU do you need for TinyLlama 1.1B Chat v0.2?

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 Q4_K (0.7 GB file, about 1.4 GB in use).

Which TinyLlama 1.1B Chat v0.2 quant should you choose?

Q4_K_M is the usual starting point for TinyLlama 1.1B Chat v0.2: it balances file size and quality well. Here it is a 0.7 GB file.

If memory is tight, the smallest file is Q4_K at 0.7 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 byTrelis
FamilyTinyllama
Licenseapache-2.0
Downloads (HF)74
Last updated2023-09-27

Frequently asked questions about TinyLlama 1.1B Chat v0.2

How much VRAM does TinyLlama 1.1B Chat v0.2 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 1.1B Chat v0.2 on an 8 GB GPU?

Yes, with Q4_K: the 0.7 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinyLlama 1.1B Chat v0.2 GGUF?

It depends on the quant: Q4_K is 0.7 GB, Q4_K_M is 0.7 GB.

What context length does TinyLlama 1.1B Chat v0.2 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 1.1B Chat v0.2 GGUF?

The files are on Hugging Face in the Trelis/TinyLlama-1.1B-Chat-v0.2-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 1.1B Chat v0.2 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 Trelis

All by Trelis →

More Tinyllama models

All Tinyllama →

Other tiny models

All tiny models →