Nemo GGUF models
182 GGUF models in the Nemo family, quantized by 44 uploaders. Sizes run from 39M to 70.6B parameters. The longest trained context is 1000K tokens.
About the Nemo GGUF models
Nemo is represented on ggufmodels.com by 182 GGUF models, quantized by 44 uploaders on Hugging Face. The most downloaded are nemo nano codec 22khz 1.89kbps 21.5fps, Nemo Gutenberg 12b v1 and Nemo Instruct 2407 MPOA v3 12B. Parameter counts run from 39M to 70.6B, and the longest trained context window is 1000K tokens.
A Q4_K_M file of a Nemo model is between 2.5 to 42.5 GB, which is the quant most people start with. Most files come from mradermacher (124), featherless-ai-quants (3) and UsernameJustAnother (3). The quants you will meet most often are Q4_K_M (142), Q5_K_M (139), Q6_K (137) and Q4_K_S (134), where the number is how many models offer that quant.
Frequently asked questions
Which Nemo GGUF should I download?
The most downloaded Nemo GGUF here is nemo nano codec 22khz 1.89kbps 21.5fps. 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 Nemo model need?
Q4_K_M files of Nemo models on this site range from 2.5 to 42.5 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 Nemo GGUF files come from?
The most common quantizers here are mradermacher, featherless-ai-quants and UsernameJustAnother. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.