LFM2.5-VL-3B

Specifications

No specifications recorded yet.

Latest developments

Liquid AI Releases LFM2.5-VL-3B-DSpark: Speculative Decoding for Vision-Language Models With Up to 3.13x Faster Decoding MarkTechPost · 3 weeks ago · 41

Accelerating vision-language models with LFM2.5-VL-DSpark Hugging Face · 3 weeks ago · 49 Liquid AI Releases LFM2.5-VL-3B: A 3B Vision-Language Model That Reads Screens, Grounds Objects, and Calls Tools On-Device MarkTechPost · 2 months ago · 26

LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge Hugging Face · 2 months ago · 22

Q3 2026

◆ Liquid AI released an experimental speculative-decoding draft model (LFM2.5-VL-DSpark) for its LFM2.5-VL-3B vision-language model Model release

◆ Liquid AI releases LFM2.5-VL-3B, an on-device vision-language model for screen understanding, object grounding, and tool/function calling Model release

• 25 Sep Liquid AI Releases LFM2.5-VL-3B-DSpark: Speculative Decoding for Vision-Language Models With Up to 3.13x Faster Decoding
• 24 Sep Accelerating vision-language models with LFM2.5-VL-DSpark
• 13 Aug Liquid AI Releases LFM2.5-VL-3B: A 3B Vision-Language Model That Reads Screens, Grounds Objects, and Calls Tools On-Device
• 12 Aug LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge

Relationships

Products & technology

• Liquid AI develops this model · 2 sources
• LFM2.5-VL-DSpark integrated with this model · 1 source
• LFM2.5-VL-3B-DSpark derived from this model · 1 source