Accelerating vision-language models with LFM2.5-VL-DSpark
• 11
AI & ML interests
A new generation of foundation models from first principles.
Recent Activity
Articles
Collection of post-trained and base LFM2.5 models.
Japanese-tuned LFMs.
-
LiquidAI/LFM2.5-1.2B-JP-202606
Text Generation • 1B • Updated • 12.1k • 78 -
LiquidAI/LFM2.5-1.2B-JP-202606-GGUF
Text Generation • 1B • Updated • 1.66k • 27 -
LiquidAI/LFM2.5-Audio-1.5B-JP
Audio-to-Audio • 1B • Updated • 294 • 80 -
LiquidAI/LFM2.5-Audio-1.5B-JP-GGUF
Audio-to-Audio • 1B • Updated • 3.2k • 32
LFM2-VL is our first series of vision-language models, designed for on-device deployment.
A family of Longevity LLMs: domain-adapted language models for aging biology
Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices
-
LiquidAI/LFM2.5-VL-3B
Image-Text-to-Text • 3B • Updated • 26k • 213 -
LFM2.5-VL-3B WebGPU
💧36Run LFM2.5-VL-3B locally in your browser with WebGPU
-
LiquidAI/LFM2.5-VL-450M
Image-Text-to-Text • 0.4B • Updated • 40.1k • 221 -
LFM2.5-VL-450M WebGPU
📹62Live video captioning and object tracking in your browser
LFM2 is a new generation of hybrid models, designed for on-device deployment.
End-to-end audio foundation model, designed for low latency and real-time conversations
Collection of post-trained and base LFM2.5 models.
Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices
Japanese-tuned LFMs.
-
LiquidAI/LFM2.5-1.2B-JP-202606
Text Generation • 1B • Updated • 12.1k • 78 -
LiquidAI/LFM2.5-1.2B-JP-202606-GGUF
Text Generation • 1B • Updated • 1.66k • 27 -
LiquidAI/LFM2.5-Audio-1.5B-JP
Audio-to-Audio • 1B • Updated • 294 • 80 -
LiquidAI/LFM2.5-Audio-1.5B-JP-GGUF
Audio-to-Audio • 1B • Updated • 3.2k • 32
-
LiquidAI/LFM2.5-VL-3B
Image-Text-to-Text • 3B • Updated • 26k • 213 -
LFM2.5-VL-3B WebGPU
💧36Run LFM2.5-VL-3B locally in your browser with WebGPU
-
LiquidAI/LFM2.5-VL-450M
Image-Text-to-Text • 0.4B • Updated • 40.1k • 221 -
LFM2.5-VL-450M WebGPU
📹62Live video captioning and object tracking in your browser
LFM2 is a new generation of hybrid models, designed for on-device deployment.
LFM2-VL is our first series of vision-language models, designed for on-device deployment.
End-to-end audio foundation model, designed for low latency and real-time conversations
A family of Longevity LLMs: domain-adapted language models for aging biology