Mfann GGUF models
139 GGUF models in the Mfann family, quantized by 4 uploaders. Sizes run from 2.78B to 8.03B parameters. The longest trained context is 500K tokens.
About the Mfann GGUF models
Mfann is represented on ggufmodels.com by 139 GGUF models, quantized by 4 uploaders on Hugging Face. The most downloaded are MFANN Phigments Slerp 4b, MFANN liminerity slerp V4 i1 and MFANN3b Rebase i1. Parameter counts run from 2.78B to 8.03B, and the longest trained context window is 500K tokens.
A Q4_K_M file of a Mfann model is between 1.7 to 4.9 GB, which is the quant most people start with. Most files come from netcat420 (75), mradermacher (58) and tensorblock (5). The quants you will meet most often are Q4_K_M (69), Q4_K_S (68), Q6_K (65) and Q5_K_S (65), where the number is how many models offer that quant.
Frequently asked questions
Which Mfann GGUF should I download?
The most downloaded Mfann GGUF here is MFANN Phigments Slerp 4b. 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 Mfann model need?
Q4_K_M files of Mfann models on this site range from 1.7 to 4.9 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 Mfann GGUF files come from?
The most common quantizers here are netcat420, mradermacher and tensorblock. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.