Bilibili Index-Translate-35B-A3B Explained: MoE Translation Model for 150 Languages
Bilibili Index-Translate-35B-A3B preview is a 35B MoE with 3B active parameters, Apache 2.0, 262K context. Architecture, translation quality caveats and.
Tencent Hy4 Explained: 770B MoE, Sherry Quantization and Open Weights
Tencent Hy4 preview explained: 770B total and 49B active MoE, Apache 2.0, Sherry quantization to about 214GB, and what it takes to run it locally.
DeepSeek V4.1 Flash Explained: MoE Architecture, KV Cache, Benchmarks
DeepSeek V4.1 Flash explained: 552B MoE with small active parameters, MIT license, KV-cache savings, benchmarks, and how to self-host or call it by API.
Mixture-of-Experts (MoE) LLM Architecture Explained (2026)
Mixture-of-Experts LLM architecture explained — routing, sparse activation, load balancing, expert parallelism, and the real serving trade-offs.