#MoE

3 articles about MoE

DeepSeek V4.1-Flash: Smarter, Faster, Cheaper — and It Beats Their Own Flagship
Open Source AI Sep 10, 2026

DeepSeek V4.1-Flash: Smarter, Faster, Cheaper — and It Beats Their Own Flagship

DeepSeek releases V4.1-Flash, a 552B asymmetric MoE that outperforms V4-Pro on benchmarks at lower cost, with a KV cache needing just 1/4 the HBM of the previous generation.

Alibaba Unveils Qwen3.8-Max: 2.4 Trillion Parameters, Claims Parity With Western Frontier Models at One-Fifth Cost
AI Research Aug 3, 2026

Alibaba Unveils Qwen3.8-Max: 2.4 Trillion Parameters, Claims Parity With Western Frontier Models at One-Fifth Cost

Alibaba released Qwen3.8-Max, a 2.4-trillion-parameter MoE model claiming parity with OpenAI and Anthropic flagships at one-fifth the cost. Priced at $2/M input and $6/M output with a 1M-token context, open weights arrive August 10.

Cohere Releases Command A+ as Open Source: 218B Parameter Enterprise Model Runs on Two H100 GPUs
AI Research May 22, 2026

Cohere Releases Command A+ as Open Source: 218B Parameter Enterprise Model Runs on Two H100 GPUs

Cohere released Command A+, a 218B parameter mixture-of-experts model, under Apache 2.0 license — targeting sovereign AI deployments with enterprise-grade agentic workflows on minimal hardware.