OP

OpenLlama 3B v2

OpenllamaGGUF by brayniacUpdated 2023-12-30
Download on Hugging Face
Parameters3.43B
Context2K
Layers26
Architecturellama
Smallest quant2.0 GB
Quick answer

OpenLlama 3B v2 needs about 5.8 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 13 quants, from 2.0 GB (Q4_0) to 6.9 GB (F16).

OpenLlama 3B v2 is a 3.43B-parameter Openllama model in GGUF format, quantized by brayniac. Its trained context length is 2K tokens. The repository has 13 quant files, from 2.0 GB (Q4_0) to 6.9 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_02.0 GB 3.2 GB
Fits Get file →
Q2_K2.1 GB 3.3 GB
Fits Get file →
Q3_K_S2.2 GB 3.4 GB
Fits Get file →
Q3_K_M2.3 GB 3.5 GB
Fits Get file →
Q3_K_L2.3 GB 3.5 GB
Fits Get file →
Q5_02.4 GB 3.6 GB
Fits Get file →
Q4_K_S2.4 GB 3.6 GB
Fits Get file →
Q4_K_M2.6 GB 3.8 GB
Fits Get file →
Q5_K_S2.6 GB 3.8 GB
Fits Get file →
Q5_K_M2.8 GB 3.9 GB
Fits Get file →
Q6_K3.6 GB 4.8 GB
Fits Get file →
Q8_03.6 GB 4.8 GB
Fits Get file →
F166.9 GB 8.0 GB
Too big Get file →

What GPU do you need for OpenLlama 3B v2?

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_K_M (2.8 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 6.9 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (6.9 GB file, about 10.1 GB in use).

Which OpenLlama 3B v2 quant should you choose?

Q4_K_M is the usual starting point for OpenLlama 3B v2: it balances file size and quality well. Here it is a 2.6 GB file.

The Q8_0 file is 3.6 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q4_0 at 2.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.43B
Layers26
Trained context2,048 tokens
KV cache (fp16)325 KB per token

Source

Quantized bybrayniac
FamilyOpenllama
Licenseapache-2.0
Downloads (HF)21
Last updated2023-12-30

Frequently asked questions about OpenLlama 3B v2

How much VRAM does OpenLlama 3B v2 need?

About 5.8 GB at Q4_K_M with an 8K context window. That is the 2.6 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 OpenLlama 3B v2 on an 8 GB GPU?

Yes, with Q6_K: the 3.6 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of OpenLlama 3B v2 GGUF?

It depends on the quant: Q4_0 is 2.0 GB, Q2_K is 2.1 GB, Q3_K_S is 2.2 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.3 GB, Q5_0 is 2.4 GB and 7 more.

What context length does OpenLlama 3B v2 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download OpenLlama 3B v2 GGUF?

The files are on Hugging Face in the brayniac/OpenLlama-3B-v2-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 OpenLlama 3B v2 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 brayniac

All by brayniac →

More Openllama models

All Openllama →

Other tiny models

All tiny models →