Open Source Multimodal AI, delivering high accuracy but with just 10% of the compute, cutting time and costs across text, audio, and video for cost-effective, accessible enterprise AI.
Aana is open intelligence.
Try Aana CTA *TBA*
Open Source Multimodal AI, delivering high accuracy but with just 10% of the compute, cutting time and costs across text, audio, and video for cost-effective, accessible enterprise AI.
Aana transforms video collections into comprehensive, in-depth answers on any topic.
Analyze videos recognizing objects and actions, integrating this information to provide a comprehensive interpretation of the content.
/search Find and interact with content effortlessly
Make your content instantly searchable with AI-driven tagging, transcription, and metadata enrichment.
/efficiency 10x real time and starting at 2$ per hour ~ 0,0005 cents per second
Scale to Petabytes of data
/efficiency 10x real time and starting at 2$ per hour ~ 0,0005 cents per second
Scale to Petabytes of data
01/ Aana is open intelligence
Open Source Multimodal AI, delivering high accuracy but with just 10% of the compute, cutting time and costs across text, audio, and video for cost-effective, accessible enterprise AI.
02/ 10x smaller model footprint
We've developed extreme quantization techniques that retain high accuracy, including the world's first usable pure 1-bit LLM.
03/ Aana is open intelligence
Open Source Multimodal AI, delivering high accuracy but with just 10% of the compute, cutting time and costs across text, audio, and video for cost-effective, accessible enterprise AI.
04/ 10x smaller model footprint
We've developed extreme quantization techniques that retain high accuracy, including the world's first usable pure 1-bit LLM.
Why Aana?
Capabi lities
10x smaller model footprint
We've developed extreme quantization techniques that retain high accuracy, including the world's first usable pure 1-bit LLM.
10-50x faster
Our kernels run Llama-3-8b at 200 tokens/sec on consumer GPUs.
Up to 40x cheaper
Our optimizations let you run 40b LLMs on consumer gaming GPUs, drastically reducing cost (e.g. Llama-3-70b on A6000 for 0.5$/hour).
