Openelm GGUF models
141 GGUF models in the Openelm family, quantized by 32 uploaders. Sizes run from 272M to 3.04B parameters. The longest trained context is 2K tokens.
About the Openelm GGUF models
Openelm is represented on ggufmodels.com by 141 GGUF models, quantized by 32 uploaders on Hugging Face. The most downloaded are OpenELM 3B Instruct, OpenELM-3B-Instruct and OpenELM 1_1B Instruct. Parameter counts run from 272M to 3.04B, and the longest trained context window is 2K tokens.
A Q4_K_M file of a Openelm model is between 0.2 to 1.9 GB, which is the quant most people start with. Most files come from RichardErkhov (66), mradermacher (17) and LiteLLMs (6). The quants you will meet most often are Q4_K_M (112), Q8_0 (110), Q6_K (98) and Q2_K (98), where the number is how many models offer that quant.
Frequently asked questions
Which Openelm GGUF should I download?
The most downloaded Openelm GGUF here is OpenELM 3B Instruct. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Openelm model need?
Q4_K_M files of Openelm models on this site range from 0.2 to 1.9 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Openelm GGUF files come from?
The most common quantizers here are RichardErkhov, mradermacher and LiteLLMs. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.