LL

Llama 3.1 Minitron 4B Depth Base

LlamaGGUF by denkijinUpdated 2024-08-24
Download on Hugging Face
Parameters4.54B
Context128K
Layers16
Architecturellama
Smallest quant2.8 GB
Quick answer

Llama 3.1 Minitron 4B Depth Base needs about 3.9 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

Llama 3.1 Minitron 4B Depth Base is a 4.54B-parameter Llama model in GGUF format, quantized by denkijin. Its trained context length is 128K tokens. The repository has 1 quant file, from 2.8 GB (Q4_K_M) to 2.8 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.8 GB 3.9 GB
Fits Get file →

What GPU do you need for Llama 3.1 Minitron 4B Depth Base?

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 (2.8 GB file, about 3.9 GB in use).

Which Llama 3.1 Minitron 4B Depth Base quant should you choose?

Q4_K_M is the usual starting point for Llama 3.1 Minitron 4B Depth Base: it balances file size and quality well. Here it is a 2.8 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters4.54B
Layers16
Trained context131,072 tokens
KV cache (fp16)64 KB per token

Source

Quantized bydenkijin
FamilyLlama
Licenseother
Downloads (HF)18
Last updated2024-08-24

Frequently asked questions about Llama 3.1 Minitron 4B Depth Base

How much VRAM does Llama 3.1 Minitron 4B Depth Base need?

About 3.9 GB at Q4_K_M with an 8K context window. That is the 2.8 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 Llama 3.1 Minitron 4B Depth Base on an 8 GB GPU?

Yes, with Q4_K_M: the 2.8 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3.1 Minitron 4B Depth Base GGUF?

It depends on the quant: Q4_K_M is 2.8 GB.

What context length does Llama 3.1 Minitron 4B Depth Base support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.

Where can I download Llama 3.1 Minitron 4B Depth Base GGUF?

The files are on Hugging Face in the denkijin/Llama-3.1-Minitron-4B-Depth-Base-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.

What license does Llama 3.1 Minitron 4B Depth Base use?

Hugging Face lists the license as other. 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 Llama-3.1-Minitron-4B-Depth-Base

Similar models

Browse all →

More from denkijin

All by denkijin →

More Llama models

All Llama →

Other small models

All small models →