# LFM2.5-VL-3B LFM2.5-VL-3B by Liquid AI: no offer with a token price is listed at present. Profile and benchmarks are on this page. - [Compare offers](https://models.searchit-agent.ai/ui-fat/modelle_vision?q=lfm2-5-vl-3b) - [View price history](https://models.searchit-agent.ai/ui-fat/modelle_vision?q=lfm2-5-vl-3b) ## Profile | Profile | | |---|---| | Developer | Liquid AI | | Type | Image models | | Origin | US | | Input types | text+bild | | Context (tokens) | 32,768 | | Max. output (tokens) | – | | Reasoning | – | | Parameters (bn) | 3.12 | | Open weights | ✓ yes | | Licence | LFM Open License | | VRAM at 4-bit (GB) | 6 (RTX PRO 4000) | | Released | – | [Open in the app](https://models.searchit-agent.ai/ui-fat/modelle_vision?q=lfm2-5-vl-3b) ## Offers with processing in the EU (0) No offers in this group. [Open in the app](https://models.searchit-agent.ai/ui-fat/modelle_vision?q=lfm2-5-vl-3b) ## Offers outside the EU (0) No offers in this group. [Open in the app](https://models.searchit-agent.ai/ui-fat/modelle_vision?q=lfm2-5-vl-3b) ## AI Act Whether the developer has signed the Code of Practice for general-purpose AI models: unknown. What this means is explained under “EU and AI Act”. [EU processing and AI Act](https://models.searchit-agent.ai/en/knowledge/eu-and-ai-act/) ## Benchmarks | Benchmarks | | |---|---:| | HallusionBench (llm-stats-Abzug) | 0.47 | | OCRBench v2, englische Spur (llm-stats-Abzug) | 0.47 | _[Report an error on this page](https://models.searchit-agent.ai/en/report/report-error/?seite=https%3A%2F%2Fmodels.searchit-agent.ai%2Fen%2Fmodels%2Flfm2-5-vl-3b%2F)_ --- Prices as of 14 Oct 2026. Providers' list prices, without guarantee.