TI

Tinyllama3

TinyllamaGGUF by faceradixUpdated 2024-07-14
Download on Hugging Face
Parameters1.92B
Context8K
Layers4
Architecturellama
Smallest quant1.3 GB
Quick answer

Tinyllama3 needs about 1.9 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Tinyllama3 is a 1.92B-parameter Tinyllama model in GGUF format, quantized by faceradix. Its trained context length is 8K tokens. The repository has 1 quant file, from 1.3 GB (Q4_K_M) to 1.3 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.3 GB 1.9 GB
Fits Get file →

What GPU do you need for Tinyllama3?

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_M (1.3 GB file, about 1.9 GB in use).

Which Tinyllama3 quant should you choose?

Q4_K_M is the usual starting point for Tinyllama3: it balances file size and quality well. Here it is a 1.3 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.92B
Layers4
Trained context8,192 tokens
KV cache (fp16)16 KB per token

Source

Quantized byfaceradix
FamilyTinyllama
Downloads (HF)29
Last updated2024-07-14

Frequently asked questions about Tinyllama3

How much VRAM does Tinyllama3 need?

About 1.9 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Tinyllama3 on an 8 GB GPU?

Yes, with Q4_K_M: the 1.3 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 Tinyllama3 GGUF?

It depends on the quant: Q4_K_M is 1.3 GB.

What context length does Tinyllama3 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.1 GB at 8K.

Where can I download Tinyllama3 GGUF?

The files are on Hugging Face in the faceradix/Tinyllama3-Q4_K_M-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 faceradix

All by faceradix →

More Tinyllama models

All Tinyllama →

Other tiny models

All tiny models →