OP

OpenELM-3B-Instruct

OpenelmGGUF by larenspearUpdated 2024-07-08
Download on Hugging Face
Parameters3.04B
Context2K
Layers36
Architectureopenelm
Smallest quant1.2 GB
Quick answer

OpenELM-3B-Instruct needs about 2.6 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 1.2 GB (Q2_K) to 3.2 GB (Q8_0).

OpenELM-3B-Instruct is a 3.04B-parameter Openelm model in GGUF format, quantized by larenspear. Its trained context length is 2K tokens. The repository has 10 quant files, from 1.2 GB (Q2_K) to 3.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.2 GB 1.7 GB
Fits Get file →
Q3_K_S1.3 GB 1.9 GB
Fits Get file →
Q3_K_M1.5 GB 2.1 GB
Fits Get file →
Q3_K_L1.7 GB 2.2 GB
Fits Get file →
Q4_K_S1.7 GB 2.3 GB
Fits Get file →
Q4_K_M1.9 GB 2.4 GB
Fits Get file →
Q5_K_S2.1 GB 2.7 GB
Fits Get file →
Q5_K_M2.2 GB 2.8 GB
Fits Get file →
Q6_K2.5 GB 3.1 GB
Fits Get file →
Q8_03.2 GB 3.8 GB
Fits Get file →

What GPU do you need for OpenELM-3B-Instruct?

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 Q6_K (2.5 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 4.1 GB in use).

Which OpenELM-3B-Instruct quant should you choose?

Q4_K_M is the usual starting point for OpenELM-3B-Instruct: it balances file size and quality well. Here it is a 1.9 GB file.

The Q8_0 file is 3.2 GB, about 1.7 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 Q2_K at 1.2 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

Architectureopenelm
Parameters3.04B
Layers36
Trained context2,048 tokens

Source

Quantized bylarenspear
FamilyOpenelm
Downloads (HF)69
Last updated2024-07-08

Frequently asked questions about OpenELM-3B-Instruct

How much VRAM does OpenELM-3B-Instruct need?

About 2.6 GB at Q4_K_M with an 8K context window. That is the 1.9 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 OpenELM-3B-Instruct on an 8 GB GPU?

Yes, with Q8_0: the 3.2 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of OpenELM-3B-Instruct GGUF?

It depends on the quant: Q2_K is 1.2 GB, Q3_K_S is 1.3 GB, Q3_K_M is 1.5 GB, Q3_K_L is 1.7 GB, Q4_K_S is 1.7 GB, Q4_K_M is 1.9 GB and 4 more.

What context length does OpenELM-3B-Instruct support?

The GGUF header lists a trained context length of 2,048 tokens (2K).

Where can I download OpenELM-3B-Instruct GGUF?

The files are on Hugging Face in the larenspear/OpenELM-3B-Instruct-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 larenspear

All by larenspear →

More Openelm models

All Openelm →

Other tiny models

All tiny models →