TI

lora model

TinyllamaGGUF by lokesh-protechUpdated 2024-08-22
Download on Hugging Face
Parameters1.1B
Context4K
Layers22
Architecturellama
Smallest quant0.7 GB
Quick answer

lora model 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_M) to 2.2 GB (F16).

lora model is a 1.1B-parameter Tinyllama model in GGUF format, quantized by lokesh-protech. Its trained context length is 4K tokens. The repository has 2 quant files, from 0.7 GB (Q4_K_M) to 2.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.7 GB 1.3 GB
Fits Get file →
F162.2 GB 2.8 GB
Fits Get file →

What GPU do you need for lora model?

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 lora model quant should you choose?

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

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.1B
Layers22
Trained context4,096 tokens
KV cache (fp16)22 KB per token

Source

Quantized bylokesh-protech
FamilyTinyllama
Licenseapache-2.0
Downloads (HF)35
Last updated2024-08-22

Frequently asked questions about lora model

How much VRAM does lora model 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 lora model 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 lora model GGUF?

It depends on the quant: Q4_K_M is 0.7 GB, F16 is 2.2 GB.

What context length does lora model support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.1 GB at 4K.

Where can I download lora model GGUF?

The files are on Hugging Face in the lokesh-protech/lora_model repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does lora model 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-bnb-4bit

Similar models

Browse all →

More Tinyllama models

All Tinyllama →

Other tiny models

All tiny models →