model

LFM2.5-VL-3B

Liquid AI's roughly 3-billion-parameter vision-language model, built for screen understanding, document reading, object grounding and tool use.

Known aliases

LFM2.5-VL

Relationships

No evidence-backed relationships are recorded.

Current clusters

build1 publisher

Liquid AI's 279.5M drafter turns a 3.13x decode gain into 2.62x end to end

Liquid AI shipped a 279.5-million-parameter draft model for LFM2.5-VL-3B on September 24, reporting 2.30x to 3.13x faster decoding on an Apple M5 Max. Image encoding and prompt prefill are unchanged, and the company's tests did not cover quantized deployments.

Publishers:runtimewire.com

Reality

Evidence55
Adoption20
Hype gap+12
Incentives72
Confidence60