Mfannv GGUF models
76 GGUF models in the Mfannv family, quantized by 4 uploaders. Sizes run from 7.24B to 8.03B parameters. The longest trained context is 128K tokens.
About the Mfannv GGUF models
Mfannv is represented on ggufmodels.com by 76 GGUF models, quantized by 4 uploaders on Hugging Face. The most downloaded are MFANNv0.22.1 i1, MFANNv0.24 i1 and MFANNv0.25 i1. Parameter counts run from 7.24B to 8.03B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Mfannv model is between 4.4 to 4.9 GB, which is the quant most people start with. Most files come from netcat420 (42), mradermacher (26) and tensorblock (4). The quants you will meet most often are Q4_K_M (39), Q6_K (34), Q4_K_S (34) and Q2_K (34), where the number is how many models offer that quant.
Frequently asked questions
Which Mfannv GGUF should I download?
The most downloaded Mfannv GGUF here is MFANNv0.22.1 i1. 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 Mfannv model need?
Q4_K_M files of Mfannv models on this site range from 4.4 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 Mfannv 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.