Cerebras beats Nvidia Blackwell in Llama 4 Maverick inference
Credit: Gorodenkoff/Shutterstock
At more than 2,500 t/s, Cerebras has set a world record for LLM inference speed on the 400B parameter Llama 4 Maverick model, the largest and most powerful in the Llama 4 family.
Register for FREE to keep reading
Join 12,000+ scientists, engineers, and IT professionals driving innovation through informatics, HPC, and simulation with:
- Insights into HPC, AI, lab informatics & data
- Curated content for life sciences, engineering & academia
- Access to Breakthroughs: real-world computing success
- Free reports & panels, including the Lab Informatics Guide
- White Papers & software updates for smarter research
Sign up now
Already a member? Log in here
Your data is protected under our privacy policy.
