PulseAugur
EN
LIVE 18:45:21

LiquidAI releases LFM2.5-VL-3B, outperforming Gemma-4 E4B locally

By PulseAugur Editorial · [1 sources] ·

LiquidAI has released LFM2.5-VL-3B, a 3.1 billion parameter vision-language model designed for local execution. This model reportedly outperforms Google's Gemma-4 E4B on screen understanding tasks, achieving a score of 82.2. The model is compatible with llama.cpp, indicating its accessibility for local deployment. AI

IMPACT This local VLM release offers a more accessible alternative for on-device AI applications, potentially increasing adoption of vision-language models.

RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

LiquidAI releases LFM2.5-VL-3B, outperforming Gemma-4 E4B locally

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    🤖 LiquidAI LFM2.5-VL-3B: a 3.1B local VLM that beats Gemma-4 E4B — screen understanding 2.5 → 82.2 LiquidAI LFM2.5-VL-3B: a 3.1B local VLM that beats Gemma-4 E4

    🤖 LiquidAI LFM2.5-VL-3B: a 3.1B local VLM that beats Gemma-4 E4B — screen understanding 2.5 → 82.2 LiquidAI LFM2.5-VL-3B: a 3.1B local VLM that beats Gemma-4 E4B — screen understanding 2.5 → 82.2 TL;DR: LiquidAI released LFM2.5-VL-3B, a 3.1B vision-language model that runs fully …

RELATED ENTITIES

RELATED TOPICS