TI

py007_tinyllama-1.1b-chat-v0.3

TinyllamaGGUF by iandennismillerUpdated 2023-10-09
Download on Hugging Face
Parameters1.1B
Context2K
Layers22
Architecturellama
Smallest quant0.6 GB
Quick answer

py007_tinyllama-1.1b-chat-v0.3 needs about 1.6 GB of memory at Q6_K (a 0.9 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_K_S) to 2.2 GB (F16).

py007_tinyllama-1.1b-chat-v0.3 is a 1.1B-parameter Tinyllama model in GGUF format, quantized by iandennismiller. Its trained context length is 2K tokens. The repository has 3 quant files, from 0.6 GB (Q4_K_S) to 2.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S0.6 GB 1.2 GB
Fits Get file →
Q6_K0.9 GB 1.4 GB
Fits Get file →
F162.2 GB 2.7 GB
Fits Get file →

What GPU do you need for py007_tinyllama-1.1b-chat-v0.3?

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 F16 (2.2 GB file, about 2.9 GB in use).

Which py007_tinyllama-1.1b-chat-v0.3 quant should you choose?

Q6_K (0.9 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q4_K_S 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 byiandennismiller
FamilyTinyllama
Licenseapache-2.0
Downloads (HF)115
Last updated2023-10-09

Frequently asked questions about py007_tinyllama-1.1b-chat-v0.3

How much VRAM does py007_tinyllama-1.1b-chat-v0.3 need?

About 1.6 GB at Q6_K with an 8K context window. That is the 0.9 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 py007_tinyllama-1.1b-chat-v0.3 on an 8 GB GPU?

Yes, with F16: the 2.2 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of py007_tinyllama-1.1b-chat-v0.3 GGUF?

It depends on the quant: Q4_K_S is 0.6 GB, Q6_K is 0.9 GB, F16 is 2.2 GB.

What context length does py007_tinyllama-1.1b-chat-v0.3 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 py007_tinyllama-1.1b-chat-v0.3 GGUF?

The files are on Hugging Face in the iandennismiller/TinyLlama-1.1B-Chat-v0.3-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 py007_tinyllama-1.1b-chat-v0.3 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.

Other GGUFs of TinyLlama-1.1B-Chat-v0.3

Similar models

Browse all →

More from iandennismiller

All by iandennismiller →

More Tinyllama models

All Tinyllama →

Other tiny models

All tiny models →