Mini GGUF models
101 GGUF models in the Mini family, quantized by 49 uploaders. Sizes run from 18M to 30.5B parameters. The longest trained context is 1000K tokens.
About the Mini GGUF models
Mini is represented on ggufmodels.com by 101 GGUF models, quantized by 49 uploaders on Hugging Face. The most downloaded are s1 mini, vllm-d3-mini and Mini-Omni2. Parameter counts run from 18M to 30.5B, and the longest trained context window is 1000K tokens.
A Q4_K_M file of a Mini model is between 0.4 to 18.6 GB, which is the quant most people start with. Most files come from mradermacher (31), Kwokou (6) and mbahrsnc (4). The quants you will meet most often are Q4_K_M (67), Q8_0 (60), Q6_K (54) and Q5_K_M (52), where the number is how many models offer that quant.
Frequently asked questions
Which Mini GGUF should I download?
The most downloaded Mini GGUF here is s1 mini. 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 Mini model need?
Q4_K_M files of Mini models on this site range from 0.4 to 18.6 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 Mini GGUF files come from?
The most common quantizers here are mradermacher, Kwokou and mbahrsnc. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.