LL

Alpaca Llama 38B InstructionTuned

LlamaGGUF by ChituyiUpdated 2024-05-25
Download on Hugging Face
Parameters510M
Context—
Layers—
Architecture—
Smallest quant0.3 GB
Quick answer

Alpaca Llama 38B InstructionTuned needs about 0.9 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Alpaca Llama 38B InstructionTuned is a 510M-parameter Llama model in GGUF format, quantized by Chituyi. The repository has 1 quant file, from 0.3 GB (Q4_K_M) to 0.3 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.3 GB 0.9 GB
Fits Get file →

What GPU do you need for Alpaca Llama 38B InstructionTuned?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (0.3 GB file, about 0.9 GB in use).

Which Alpaca Llama 38B InstructionTuned quant should you choose?

Q4_K_M is the usual starting point for Alpaca Llama 38B InstructionTuned: it balances file size and quality well. Here it is a 0.3 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters510M

Source

Quantized byChituyi
FamilyLlama
Licenseapache-2.0
Downloads (HF)31
Last updated2024-05-25

Frequently asked questions about Alpaca Llama 38B InstructionTuned

How much VRAM does Alpaca Llama 38B InstructionTuned need?

About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.3 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 Alpaca Llama 38B InstructionTuned on an 8 GB GPU?

Yes, with Q4_K_M: the 0.3 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Alpaca Llama 38B InstructionTuned GGUF?

It depends on the quant: Q4_K_M is 0.3 GB.

Where can I download Alpaca Llama 38B InstructionTuned GGUF?

The files are on Hugging Face in the Chituyi/Alpaca-Llama-38B-InstructionTuned repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Alpaca Llama 38B InstructionTuned 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 Chituyi

All by Chituyi →

More Llama models

All Llama →

Other tiny models

All tiny models →