Up to 3.2x Faster Inference with LFM2.5-DSpark
• 41
AI & ML interests
A new generation of foundation models from first principles.
Articles
Article
Up to 3.2x Faster Inference with LFM2.5-DSpark
LiquidAI
• • 41 Article
LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation
LiquidAI
• • 34 Article
LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge
LiquidAI
• • 49 Article
Deploy local agents everywhere with LFM2.5-2.6B
LiquidAI
• • 92 Article
LFM2.5-Encoders for Fast Long-Context Inference on CPU
LiquidAI
• • 68