DEV Community

#moe

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
DeepSeek R1: The Open-Source Reasoning Revolution That Changes Everything

DeepSeek R1: The Open-Source Reasoning Revolution That Changes Everything

Comments
2 min read
FreeToken Runs Frontier-Scale MoE Models by Treating the Whole PC as the Inference Platform

FreeToken Runs Frontier-Scale MoE Models by Treating the Whole PC as the Inference Platform

Comments 1
5 min read
Your Intel Laptop Can Run 30B Models Now. No NVIDIA. No Cloud. No Problem.

Your Intel Laptop Can Run 30B Models Now. No NVIDIA. No Cloud. No Problem.

Comments
11 min read
How a 176 KB C Binary Runs a 2.78-Trillion-Parameter Model on One CPU with 8 GB of RAM

How a 176 KB C Binary Runs a 2.78-Trillion-Parameter Model on One CPU with 8 GB of RAM

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

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

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

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

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

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

Comments
3 min read
Step 3.7 Flash is a drop-in — except for one endpoint detail

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

1
Comments
9 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.