Published by TokForge for on-device inference.
TokForge
- Website: https://tokforge.ai
- Discord: https://discord.gg/Acv3CBtfVm
- Google Play: https://play.google.com/store/apps/details?id=dev.tokforge
- iOS TestFlight: https://testflight.apple.com/join/jnufjzRr
Runs on-device in the TokForge app (version 1.3.9.7 or newer).
LFM3-1.7B-MNN
Pre-converted LFM3 1.7B in MNN format for on-device inference with TokForge.
Original model by Liquid AI, converted to MNN 4-bit for mobile deployment. This is a modified (converted and quantized) version of the original model; it is distributed under the LFM Open License v1.0 (see
LICENSE).
Model Details
| Architecture | LFM3 hybrid (13 short-convolution layers, 6 full-attention and 5 sliding-window attention layers, GQA 16Q/4KV) |
| Parameters | 1.7B (4-bit quantized) |
| Format | MNN (Alibaba Mobile Neural Network) |
| Quantization | int4 weights, block size 32, HQQ, tied embedding and head in the weight file |
| Vocab | 128,000 tokens |
| Source | LiquidAI/LFM3-1.7B |
Description
Liquid AI's LFM3 1.7B, a compact hybrid model built for edge devices: most layers are short convolutions, so memory stays low on long chats. Good general chat and instruction following in a small download.
Files
| File | Description |
|---|---|
llm.mnn |
Model computation graph |
llm.mnn.json |
Graph description |
llm.mnn.weight |
Quantized weight data (int4, block=32) |
llm_config.json |
Model config with the chat template |
tokenizer.mtok |
Tokenizer |
config.json |
MNN runtime config |
Usage with TokForge
This model needs the LFM3 support in TokForge 1.3.9.7 or newer, a free Android app for private, on-device LLM inference.
- Download TokForge from Google Play
- Open the app, then Models, then download this model
- Start chatting: runs locally, no internet required
Credits
- LFM3 1.7B by Liquid AI (Hugging Face), licensed under the LFM Open License v1.0
- MNN by Alibaba (GitHub)
- Downloads last month
- 189