AI Model2026
Runs LFM3-1.7B locally on CPUs and GPUs using the GGUF format. Multiple quantizations are available, including a Q4_0 checkpoint trained to recover accuracy lost during quantization.
Runs LFM3-1.7B locally on CPUs and GPUs using the GGUF format. Multiple quantizations are available, including a Q4_0 checkpoint trained to recover accuracy lost during quantization.