Model overview
What this model is for
lfm3-vl:2b is a compact vision-language model suited to on-device image-and-text understanding, with tool-calling listed as a capability. It can be considered for applications that need to interpret visual inputs alongside text, such as image-aware assistants, visual question answering, document or screen understanding, and agent workflows that combine visual context with external tools. The supplied material identifies its modalities as image and text and describes its primary use case as vision. Its 2-billion-parameter size may be relevant when evaluating local deployment constraints, although the supplied material does not provide memory requirements, latency measurements, hardware guidance, or an inference speed benchmark. No context-window value is available in the supplied material, so suitability for long documents or extended conversations cannot be assessed from these details. Pricing information is also unavailable. The supplied material does not provide licensing terms, safety details, training-data information, evaluation results, or broader performance comparisons; review the applicable Ollama or model documentation before production use. The source page explicitly describes it as intended for on-device visual understanding.