NVIDIA said it has achieved a record for large language model inference, announcing that an NVIDIA DGX B200 node with eight Blackwell GPUs achieved more than 1,000 tokens ….
AI Inference: NVIDIA Reports Blackwell Surpasses 1000 TPS/User Barrier with Llama 4 Maverick
May 23, 2025 by
Multiverse Says It Compresses Llama Models by 80%
April 8, 2025 by
Multiverse Computing today released two new AI models compressed by CompactifAI, Multiverse’s AI compressor: 80 percent compressed versions of Llama 3.1-8B and Llama 3.3-70B. Both models have 60 percent fewer parameters than the original models, 84 percent greater energy effi ciency ….
