First reported by Twitter / X
Tencent Releases Hy3: A 295B-Parameter MoE AI Model with 21B Active Parameters
Tencent Launches Hunyuan Hy3 LLM with Strong Enterprise Performance
By
tech360.tv
23h ago
Source
tech360.tvTencent Launches Hunyuan Hy3 LLM with Strong Enterprise Performancetech360.tvTencent has launched its Hunyuan Hy3 large language model. This model features a Mixture of Experts architecture. It includes 295 billion total parameters with 21 billion activated, supporting a 256K context length. The model reportedly achieves a 90 per cent task resolution rate on Tencent's WorkBuddy enterprise platform, according to Tencent Tech.
You might also wanna read
Tencent Releases Hy3: A 295B-Parameter MoE AI Model with 21B Active Parameters
Tencent's Hy Team has released Hy3, a 295B-parameter Mixture-of-Experts (MoE) AI model with 21B active parameters and 3.8B MTP layer paramet
huggingface.co·2d ago
Tencent's Apache-licensed Hy3 takes on GLM-5.2 at half the size — and wins everywhere except coding
venturebeat.com·1d ago
Tencent's Apache-licensed Hy3 takes on GLM-5.2 at half the size — and wins everywhere except coding
VentureBeat·1d ago
Hy3 (free) - API Pricing & Providers
openrouter.ai·1d ago
Tencent's HunyuanWorld 1.0: Open-Source Model for 3D World Generation
HunyuanWorld 1.0 by Tencent is an open-source model that generates immersive, explorable 3D worlds from a single text prompt or image. It ex
Product Hunt·11mo ago
Tencent Releases Open-Source Hunyuan3D-2.1 AI for Generating High-Fidelity 3D Assets from Images
Tencent has released Hunyuan3D-2.1, a fully open-source AI model for generating high-fidelity 3D assets with physically-based rendering (PBR
Product Hunt·1y ago
Tencent ships Hy3 as an Apache 2.0 agent model
runtimewire.com·1d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.