privacy-filter: hardware requirements

privacy-filter needs about 1.4 GB of memory at Q4 quantization — a 845 MB download plus room for context and overhead. That fits a machine with 8GB RAM.

Parameters
1.4B
Tier
Runs on a laptop
Licence
See model card
Released
2026-04-22

This is a mixture-of-experts model. Only a fraction of its 1.4B parameters are used for each token, so it runs faster than its size suggests — but all of it still has to fit in memory. The speed is that of a small model; the memory requirement is that of a large one. More on this →

Will it run on your machine?

Download sizes by quantization

Lower quantization means a smaller file and less memory, at some cost to quality. Q4_K_M is the usual starting point. What is this?

QuantDownloadRAM @ 4KRAM @ 32KSource
Q4_K_Mrecommended845 MB1.4 GB1.5 GBestimated
Q5_K_M992 MB1.5 GB1.7 GBestimated
Q6_K1.1 GB1.7 GB1.8 GBestimated
Q8_01.5 GB2.0 GB2.2 GBestimated
BF162.8 GB3.4 GB3.5 GBestimated

“Measured” sizes are read from published GGUF files. “Estimated” sizes are derived from the parameter count and are typically within a few percent. The RAM columns add the context cache and runtime overhead to the download size.

Model card on HuggingFace →API specs & pricing →Verified 2026-08-09Tracked for 12 months after release