Tag
6 articles
NVIDIA introduces Nemotron-Labs-3-Puzzle-75B-A9B, a compressed hybrid MoE LLM delivering 2.03x server throughput, leveraging hardware-aware compression and knowledge distillation.
JetBrains has released Mellum2, a 12-billion parameter MoE model trained on 10.6 trillion tokens, designed to accelerate specialized AI tasks in multi-model pipelines.
This explainer explores the advanced Mixture of Experts (MoE) architecture used in Liquid AI's LFM2.5-8B-A1B model, examining how sparse parameter activation enables powerful on-device AI capabilities.
This article explains the advanced AI concepts behind Qwen 3.6-35B-A3B, a multimodal model that combines MoE routing, RAG, and session persistence for intelligent, context-aware AI applications.
Alibaba's Qwen team open-sources Qwen3.6-35B-A3B, a sparse MoE vision-language model with 3B active parameters and agentic coding capabilities.
This explainer article dives into NVIDIA's Nemotron-Cascade 2, an advanced Mixture-of-Experts (MoE) model that demonstrates how strategic parameter allocation can enhance reasoning capabilities while maintaining computational efficiency.
