mixture of experts model Articles
Browse 11 articles about mixture of experts model.

LongCat 2.5: Meituan's 1.6T Model Looks Good on Paper, Shaky in Practice
LongCat 2.5 is Meituan's 1.6T parameter MoE model for agentic coding. Hands-on tests show gaps between its benchmarks and real output.

Sage A1.5 Tested: Intern's 35B Agentic Research Model Explained
Sage A1.5 is a 35B MoE agentic model from InternScience, tested locally on physics simulation and fact-checking tasks against GLM and Kimi benchmarks.

Meta Muse Spark Open: Specs, Benchmarks, and How It Compares
Meta's 816B Muse Spark Open claims the top US open-weight model spot. Here's how it benchmarks, licenses, and runs against Chinese rivals.

LFM2.5-24B-A2B: Inside LiquidAI's New Agentic MoE Model
LiquidAI's LFM2.5-24B-A2B packs 24B total/2B active params, 131K context, and strong agentic benchmarks for on-device reasoning.

Reflection AI Beam: 501B Open Weight Model, Explained
Reflection AI's Beam packs 501B total parameters, 23B active, trained on 23.8T tokens, and is set for an Apache 2.0 release.

Xing4.0-29B-A4B: China Telecom's Agent-Focused MoE Model, Explained
Xing4.0-29B-A4B is China Telecom's new 29B MoE model trained on Ascend NPUs, benchmarked against Gemma4-26B-A4B and Qwen3.6-35B-A3B.

DeepSeek V4.1 Flash Benchmarks vs Opus 5 and GPT-5.6: What's Real?
DeepSeek V4.1 Flash matches Opus 5 and GPT-5.6 on paper, but hands-on coding tests expose a gap between benchmark scores and real output.

Tencent Hy4 Preview: A 770B MoE Model That Edges Out GLM-5.3
Tencent's Hy4 preview is a 770B-parameter, 49B-active MoE model with 1M context that beat GLM-5.3 and Kimi K3 in blind evals.

Qwen3.8-Flash-Next: Inside the Qwen 4 Architecture Preview
Qwen3.8-Flash-Next previews Qwen 4's architecture: hybrid gated-delta and sparse attention, engram embeddings, 125B params, 6B active.

Ornith 1.5 35B-A3B: Local Deployment, VRAM, and Real-World Tests
Ornith 1.5 35B-A3B is a mixture-of-experts model with 3B active params. Here's how it runs locally on an A100, and how it handles agentic and reasoning tests.

Poolside's Laguna S 2.1: A 118B Open Model for Local Agentic Coding
Poolside's open-weight Laguna S 2.1 runs agentic coding locally at 80+ tokens/sec on DGX Spark, matching models ten times its size.