Mamba GGUF models
90 GGUF models in the Mamba family, quantized by 25 uploaders. Sizes run from 129M to 7.27B parameters. The longest trained context is 1024K tokens.
About the Mamba GGUF models
Mamba is represented on ggufmodels.com by 90 GGUF models, quantized by 25 uploaders on Hugging Face. The most downloaded are mamba 130m hf, Mamba2 130m Hf and Mamba 370m Hf. Parameter counts run from 129M to 7.27B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Mamba model is between 0.1 to 4.4 GB, which is the quant most people start with. Most files come from mradermacher (40), RichardErkhov (12) and tensorblock (8). The quants you will meet most often are Q2_K (71), Q3_K_M (66), Q4_K_M (65) and Q6_K (64), where the number is how many models offer that quant.
Frequently asked questions
Which Mamba GGUF should I download?
The most downloaded Mamba GGUF here is mamba 130m hf. 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 Mamba model need?
Q4_K_M files of Mamba models on this site range from 0.1 to 4.4 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 Mamba GGUF files come from?
The most common quantizers here are mradermacher, RichardErkhov 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.