LF

LFM2 350M PII Extract JP

LfmGGUF by LiquidAIUpdated 2026-08-06
Download on Hugging Face
Parameters354M
Context125K
Layers16
Architecturelfm2
Smallest quant0.2 GB
Quick answer

LFM2 350M PII Extract JP needs about 1.3 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.2 GB (Q4_0) to 0.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

LFM2 350M PII Extract JP – on‑device Japanese PII extraction

LFM2 350M PII Extract JP is a 0.354 billion parameter model trained to extract personally identifiable information from Japanese text. It outputs results in JSON format for easy masking of sensitive data. The model runs locally via llama.cpp.

Good at

  • Japanese PII extraction
  • JSON output for masking
  • On‑device processing

Limits

  • No vision support
  • License is other
  • Context limited to 128000 tokens

Best for

  • Contract de‑identification
  • Email privacy filtering
  • Medical record anonymisation

Who it’s for. Developers building privacy‑aware Japanese applications that need fast, local PII extraction. The model is suitable for edge devices and small‑scale deployments where cloud access is limited.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.2 GB 1.3 GB
Fits Get file →
Q4_K_M0.2 GB 1.3 GB
Fits Get file →
Q5_K_M0.3 GB 1.3 GB
Fits Get file →
Q6_K0.3 GB 1.3 GB
Fits Get file →
Q8_00.4 GB 1.4 GB
Fits Get file →
F160.7 GB 1.7 GB
Fits Get file →

For 8 GB VRAM, use Q4_0, Q4_K_M, or Q5_K_M – each file is 0.22–0.26 GB and requires about 1.3 GB memory at 8 k context. If more precision is needed and you have 12 GB VRAM, Q8_0 (0.38 GB) or F16 (0.71 GB) can be used, requiring 1.4–1.7 GB memory.

What GPU do you need for LFM2 350M PII Extract JP?

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 (0.7 GB file, about 1.7 GB in use).

Which LFM2 350M PII Extract JP quant should you choose?

Q4_K_M is the usual starting point for LFM2 350M PII Extract JP: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 0.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q4_0 at 0.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters354M
Layers16
Trained context128,000 tokens
KV cache (fp16)64 KB per token

Source

Quantized byLiquidAI
FamilyLfm
Licenseother
Downloads (HF)744
Last updated2026-08-06

Frequently asked questions about LFM2 350M PII Extract JP

How much VRAM does LFM2 350M PII Extract JP need?

About 1.3 GB at Q4_K_M with an 8K context window. That is the 0.2 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 LFM2 350M PII Extract JP on an 8 GB GPU?

Yes, with F16: the 0.7 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2 350M PII Extract JP GGUF?

It depends on the quant: Q4_0 is 0.2 GB, Q4_K_M is 0.2 GB, Q5_K_M is 0.3 GB, Q6_K is 0.3 GB, Q8_0 is 0.4 GB, F16 is 0.7 GB.

What context length does LFM2 350M PII Extract JP support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.

Where can I download LFM2 350M PII Extract JP GGUF?

The files are on Hugging Face in the LiquidAI/LFM2-350M-PII-Extract-JP-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 LFM2 350M PII Extract JP use?

Hugging Face lists the license as other. 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 LFM2 350M PII Extract JP on 8 GB VRAM?

Yes, the Q4_0, Q4_K_M, and Q5_K_M quantizations fit within 8 GB VRAM, each needing about 1.3 GB at 8 k context.

Does the model support English text?

The model is trained for Japanese PII extraction; English support is not guaranteed.

What license applies to this model?

The model is licensed under an "other" license, see the LICENSE file on the repository.

Other GGUFs of LFM2-350M-PII-Extract-JP

Similar models

Browse all →

More from LiquidAI

All by LiquidAI →

More Lfm models

All Lfm →

Other tiny models

All tiny models →