Mistral AI’s Post

Mistral AI reposted this

View organization page for NVIDIA AI, graphic

974,337 followers

Let the Mistral AI MoE tokens fly 📈 🚀 #Mixtral 8x7B with NVIDIA #TensorRT #LLM on #H100. ➡️ https://nvda.ws/3L5WIZ0

  • No alternative text description for this image
Clayton Ford

Senior Designer - AI | UX | Digital & Physical Prototyping - Breaking problems into pieces.

3w

Mixtral 8x7B - 2x H100's - ~$5/hr - 60 tokens/s - 216 thousand tokens/hour - $23.15/million tokens ///// Groq - 575 tokens/s - $0.24/million tokens - $0.50/hr - 2.07 million tokens/hour Weird flex, but I guess what other hardware could you buy... For now

Charles Pierce Belden

Partner - Cyber Security and Insurance Innovation Practice

3w

Mixture of Experts (MoE) optimize query expense, better response time, reduced compute power necessary, and rewarding domain specific expertise. Use-Case: LLM trained in Cyber Security hosting an AI Security Agent, as an identity on a network. Securing IT (Information Technology), IoT (Internet of Things, drones), OT (Operational Technology), ICS (Industrial Control Systems), Critical Infrastructure, and human endpoints is too large an attack surface for human capabilities alone. AI presents new unique challenges to cyber security and solving the problem requires an AI solution. Secure AI computing is an immediate concern.

Paul T.

El Tecnologico de la Influencia@UHTN Ultra-High-Technology-Network

3w

Exciting🚀Thanks for sharing💯🤠

Jordan Bird

PhD | Senior Lecturer in Computer Science | Deputy B11 REF Co-ordinator

3w

Excellent ! However the both did not answer the request of my students 🤔 for a talk.

Ignacio Garcia

AI Specialist | Deep Learning Engineer | Ex-Twitter | Data Science Enthusiast

3w

Amazing! Love it !!

Dennis Allen

VP of Product @ Shulman & Hill | Designing AI Solutions

3w

Can't wait!

William Hill

AI Product Marketing Manager @ NVIDIA | Duke MBA

3w

Very cool image

See more comments

To view or add a comment, sign in

Explore topics