Moe - DEV Community

Skip to content

DEV Community

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Pneumetron

Jul 13

NVIDIA Unveils Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4: A Deployment-Optimized Hybrid MoE LLM

#nvidia #nemotron3puzzle #llm #moe

4 min read

overthelex

Jul 3

2 TB of Ukrainian Law + DeepSeek V3 860B on GCP: What We'd Get

#deepseekv3 #moe #tpuv5p #gcp

7 min read

Jun 30

Scaling MoE Models with LongCat-2.0: A Deep Dive into 1.6T Parameter Architecture Design

#ai #moe #models #longcat

3 min read

Creeta

Jun 18

Step 3.7 Flash is a drop-in — except for one endpoint detail

#stepfun #step37flash #llm #moe

9 min read

Jovan Chan

Jun 12

Kimi K2.6 for Local AI in 2026: What VRAM and System RAM You Need to Actually Run the 1T-Parameter MoE Coding Leader

#kimik2 #localllm #moe #hardwareguide

6 min read

Randy AP

May 27

I built a Rust inference engine that streams MoE expert weights from NVMe SSDs, no GPU required

#ai #rust #moe

2 min read

May 5

Mistral Large 3: The 675B Open-Weight MoE Model Developer Guide

#mistral #llm #opensource #moe

5 min read

Thousand Miles AI

May 22

ZAYA1-8B: a 760M-active MoE trained on AMD MI300x

#ai #llm #moe #openweights

5 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.