Get the app
Machine LearningDev3 min reading time

LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation

Hugging Face
Read full post
LiquidAI has released Quantization-Aware Distillation (QAD) Q4_0 GGUF checkpoints for LFM2.5 models ranging from 230M to 2.6B parameters. These checkpoints maintain 97% of the original model accuracy while enabling 4-bit quantization speed and memory efficiency on various edge devices.
#edge-inference#lfm2-5#liquidai#llama-cpp#model-compression#model-quantization

More in Machine Learning

Machine Learning3 min read

Anthropic caught scientists using Claude to further biological weapon research

Covered by 2 sources
Machine Learning4 min read

DeepSeek launches V4.1-Flash and retires V4-Pro, its flagship model

Covered by 2 sources
Machine Learning4 min read

Mistral wants open-weight AI to compete at the frontier. It just raised $3.5 billion to do it.

The New Stack (AI)