LFM2-VL is our first series of vision-language models, designed for on-device deployment.
			
	
	AI & ML interests
A new generation of foundation models from first principles.
Recent Activity
	View all activity
	
			models
			32
		
			
	
	
	
	
	 
				LiquidAI/LFM2-350M-PII-Extract-JP
			Text Generation
			• 
		
				0.4B
			• 
	
				Updated
					
				
				• 
					
					421
				
	
				• 
					
					39
				
 
				LiquidAI/LFM2-VL-450M
			Image-Text-to-Text
			• 
		
				0.5B
			• 
	
				Updated
					
				
				• 
					
					9.62k
				
	
				• 
					
					128
				
 
				LiquidAI/LFM2-VL-3B
			Image-Text-to-Text
			• 
		
				3B
			• 
	
				Updated
					
				
				• 
					
					1.25k
				
	
				• 
					
					66
				
 
				LiquidAI/LFM2-VL-1.6B
			Image-Text-to-Text
			• 
		
				2B
			• 
	
				Updated
					
				
				• 
					
					6.94k
				
	
				• 
					
					201
				
 
				LiquidAI/LeapBundles
		
	
				Updated
					
				
				
				
	
				• 
					
					5
				
 
				LiquidAI/LFM2-VL-3B-GGUF
			Image-Text-to-Text
			• 
		
				3B
			• 
	
				Updated
					
				
				• 
					
					5.16k
				
	
				• 
					
					14
				
 
				LiquidAI/LFM2-350M-ENJP-MT
			Translation
			• 
		
				0.4B
			• 
	
				Updated
					
				
				• 
					
					6.18k
				• 
			
	
				• 
					
					60
				
 
				LiquidAI/LFM2-350M-Math
			Text Generation
			• 
		
				0.4B
			• 
	
				Updated
					
				
				• 
					
					1.32k
				
	
				• 
					
					39
				
 
				LiquidAI/LFM2-1.2B-Tool
			Text Generation
			• 
		
				1B
			• 
	
				Updated
					
				
				• 
					
					1.12k
				
	
				• 
					
					75
				
 
				LiquidAI/LFM2-1.2B-RAG
			Text Generation
			• 
		
				1B
			• 
	
				Updated
					
				
				• 
					
					2.25k
				
	
				• 
					
					87
				
			datasets
			0
		
			
	None public yet