Keyword

Liquid AI LFM3

Appears in 3 articles·Latest Nov 2, 2026

Exploded cutaway of a small 1.7B-parameter language model block beside a memory module, a long context ribbon, a thinking toggle, and a fine-tuning adapter layer.

Nov 2, 2026

LFM3-1.7B-Base: Specs, Memory Needs and Fine-Tuning Guide

Liquid AI's LFM3-1.7B-Base is a 1.73B model with 256K context that takes about 1 GB at 4-bit. Specs, inference code, thinking toggle and fine-tuning with TRL.

LFM3-1.7B-BaseLiquid AI LFM3LFM3 fine-tuning

Diagram-style illustration of a small language model running locally: model file formats feed a compact machine whose weight block and runtime tools produce a stream of output tokens passing through test gates.

Oct 29, 2026

How to Run LFM3-1.7B Locally and What It Can Actually Do

Run Liquid AI's LFM3-1.7B locally with llama.cpp, Ollama, LM Studio or MLX. Covers formats, sampling settings, and which tests passed or failed in hands-on use.

LFM3 1.7Brun LFM3 locallyLiquid AI LFM3

A small language model cube, half sealed and half opened into a layered quantized-weight lattice, connected to a phone and a laptop beside a row of checkpoint format cartridges and sampling dials.

Oct 28, 2026

How to Run LFM3-1.7B Locally: Hardware, Formats, Settings

Run Liquid AI's LFM3-1.7B on a phone or laptop: GGUF, MLX, ONNX, FP8 and NVFP4 checkpoints, sampling settings, tool calling, and where it falls short.

LFM3-1.7BLiquid AI LFM3run LFM3 locally