Privacy Filter Multilingual needs about 2.2 GB of memory at its main file (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.6 GB to 2.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.1 GB.
Multilingual PII detection with 54 categories across 16 languages
Privacy Filter Multilingual is a 1.4B‑parameter MoE model fine‑tuned for token‑classification of PII. It outputs BIOES tags for 54 categories in 16 languages. The GGUF package supports F16 and unknown quantizations.
Good at
- Fine‑grained PII extraction
- Multilingual token classification
- BIOES span decoding
Limits
- Requires 8‑k context for memory estimates
- Not a chat or vision model
- No Python runtime needed, only custom GGML engine
Best for
- PII redaction pipelines
- Data privacy compliance checks
- Local deployment of PII detectors
Who it’s for. Developers building privacy‑aware applications that need local, language‑agnostic PII detection. The model is suitable for integration via OpenMed or custom GGML runtimes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.6 GB | 2.2 GB | Fits | Get file → | |
| F16 | 2.8 GB | 3.4 GB | Fits | Get file → |
For 8‑k context, the F16 quant uses about 3.4 GB VRAM and 2.2 GB RAM. The unknown quant is smaller at 1.64 GB file size, estimating 2.2 GB VRAM. Choose F16 for higher precision, unknown for tighter memory budgets. Estimates are approximate.
What GPU do you need for Privacy Filter Multilingual?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is F16 (2.8 GB file, about 3.4 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Privacy Filter Multilingual
How much VRAM does Privacy Filter Multilingual need?
About 2.2 GB at its main file with an 8K context window. That is the 1.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Privacy Filter Multilingual on an 8 GB GPU?
Yes, with F16: the 2.8 GB file needs about 3.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Privacy Filter Multilingual GGUF?
It depends on the quant: file is 1.6 GB, F16 is 2.8 GB.
What context length does Privacy Filter Multilingual support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.0 GB at 8K and 0.1 GB at 32K.
Where can I download Privacy Filter Multilingual GGUF?
The files are on Hugging Face in the LocalAI-io/privacy-filter-multilingual-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Privacy Filter Multilingual use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, the F16 quant uses roughly 3.4 GB VRAM at 8‑k context, well within an 8 GB limit.
Does it support vision or chat?
No, it is a token‑classification model only and does not provide vision or chat capabilities.
What license applies?
The model is released under the Apache‑2.0 license.