Liquid AI Releases LFM3
Liquid AI keeps pushing its non-transformer bet, and LFM3 is a coherent step: six open-weight 2B-class multimodal models with a 256K context window that fit in roughly a gigabyte at 4-bit. In our view the real story is the tri-hybrid backbone — if it matches transformer quality at this size, edge and on-device developers get a serious alternative to Gemma and Qwen small models.… more
The 'decisions' modality also hints at agentic and control use cases, which is where Liquid has always tried to differentiate. It is not a frontier-shaking launch, but for the fast-growing small-model segment it is a meaningful shot. Worth waiting for independent benchmarks before declaring victory.
Liquid AI Releases LFM3: 6 Open-Weight 2B-Class Multimodal Models
Liquid AI released LFM3, 6 open-weight 2B-class models for text, vision, audio, omni and decisions. LFM3-1.7B uses a tri-hybrid backbone, a 256K context window and fits in about 1 GB at 4-bit. The post Liquid AI Releases LFM3: 6 Open-Weight 2B-Class Multimodal Models appeared first …
Source:
Marktechpost
Discussion (0)