LL

Llama 2 4B

LlamaGGUF by AryanneUpdated 2023-09-23
Download on Hugging Face
Parameters3.5B
Context4K
Layers16
Architecturellama
Smallest quant1.5 GB
Quick answer

Llama 2 4B needs about 4.7 GB of memory at Q4_0 (a 2.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 1.5 GB (Q2_K) to 2.4 GB (Q5_0).

Llama 2 4B is a 3.5B-parameter Llama model in GGUF format, quantized by Aryanne. Its trained context length is 4K tokens. The repository has 3 quant files, from 1.5 GB (Q2_K) to 2.4 GB (Q5_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.5 GB 3.1 GB
Fits Get file →
Q4_02.0 GB 3.6 GB
Fits Get file →
Q5_02.4 GB 4.0 GB
Fits Get file →

What GPU do you need for Llama 2 4B?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q5_0 (2.4 GB file, about 5.1 GB in use).

Which Llama 2 4B quant should you choose?

Q4_0 (2.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K at 1.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.5B
Layers16
Trained context4,096 tokens
KV cache (fp16)256 KB per token

Source

Quantized byAryanne
FamilyLlama
Downloads (HF)64
Last updated2023-09-23

Frequently asked questions about Llama 2 4B

How much VRAM does Llama 2 4B need?

About 4.7 GB at Q4_0 with an 8K context window. That is the 2.0 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 2 4B on an 8 GB GPU?

Yes, with Q5_0: the 2.4 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 2 4B GGUF?

It depends on the quant: Q2_K is 1.5 GB, Q4_0 is 2.0 GB, Q5_0 is 2.4 GB.

What context length does Llama 2 4B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.1 GB at 8K and 1.1 GB at 4K.

Where can I download Llama 2 4B GGUF?

The files are on Hugging Face in the Aryanne/Llama-2-4B-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 Aryanne

All by Aryanne →

More Llama models

All Llama →

Other tiny models

All tiny models →