LFM3-1.7B-GGUF
★ agentic
Overview
LFM3-1.7B at Q4_K_M - a 1.1 GB download that runs full agent harnesses (tool calling, deferred tool search, structured output) on phones and laptops, with the full 256K context window.
Good for
- agentic
Recommended hardware
≈ 4 GB VRAM to run this 1.7B model at the Q4_K_M quantization.
Fits 4 GB+ consumer GPUs (e.g. GTX 1650), or CPU inference