Tagged: vision-language-model

6 articles

Latest

Liquid AI's 3B vision model hits 228 tokens/s on M5 Max, 11K/s on GPU

Meta’s 30B Muse Glimmer launches open-source: A 2B vision encoder meets hybrid attention

IBM's 3B Granite Vision model beats much larger rivals at reading charts

NVIDIA's Cosmos Reason 2 tops physical AI charts, giving robots better common sense

SmolVLM packs video analysis and 16x faster throughput into a 2B model

Falcon 2 hits 11B parameters, matching Falcon-40B at a quarter of the size