Minerva GGUF models
70 GGUF models in the Minerva family, quantized by 21 uploaders. Sizes run from 30M to 79.7B parameters. The longest trained context is 1000K tokens.
About the Minerva GGUF models
Minerva is represented on ggufmodels.com by 70 GGUF models, quantized by 21 uploaders on Hugging Face. The most downloaded are Minerva 3B base v1.0, Minerva 3B base RAG and Minerva. Parameter counts run from 30M to 79.7B, and the longest trained context window is 1000K tokens.
A Q4_K_M file of a Minerva model is between 0.3 to 48.5 GB, which is the quant most people start with. Most files come from mradermacher (23), roleplaiapp (12) and mudler (8). The quants you will meet most often are Q4_K_M (34), Q6_K (32), Q5_K_M (32) and Q3_K_M (29), where the number is how many models offer that quant.
Frequently asked questions
Which Minerva GGUF should I download?
The most downloaded Minerva GGUF here is Minerva 3B base v1.0. 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 Minerva model need?
Q4_K_M files of Minerva models on this site range from 0.3 to 48.5 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 Minerva GGUF files come from?
The most common quantizers here are mradermacher, roleplaiapp and mudler. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.