Buy Crypto
Pay with
USD
USD
Buy & Sell
Hot
Supports Visa, Mastercard, SEPA & more
P2P
0 Fees
Flexible trading, zero fees
Gate Card
Use your crypto for payments worldwide
Markets
Trade
Basic
Advanced
Futures
Futures
Access hundreds of perpetual contracts
CFD
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Introduction to Futures Trading
Learn the basics of futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to practice risk-free trading
Stocks
CFD
Stock CFD Derivatives
US Stocks
Access real US stocks and ETFs
HK Stocks
Trade quality Hong Kong-listed stocks
Korean Stocks
SK Hynix
Real Korean stocks and top assets
Stock Futures
High leverage, 24/7 trading
Tokenized Stocks
Backed by real stock assets
IPO Access
Unlock full access to global stock IPOs
GUSD
3.8%
Mint GUSD for Treasury RWA yields
Stocks Activities
Trade Popular Stocks and Unlock Generous Airdrops
Earn
Launch
CandyDrop
tag
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
IPO Access
tag
Unlock full access to global stock IPOs
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
Investment
Square
Square
Post, share, and explore crypto trends
Live
moments live
Live crypto market analysis
Chat
Chat with crypto traders
News
What is happening in crypto
flower_head
More
Promotions
AI
Others
TradFi（新）
JMKE IPO
Rewards

AMD Releases Fully Open-Source Instella-MoE Model with 16B Parameters on July 25

GateNews
AI Industry News
AMD-3.29%
According to BlockBeats, AMD released fully open-source mixture-of-experts (MoE) model Instella-MoE on July 25, featuring 16 billion total parameters with 2.8 billion parameters activated per token. The foundational model achieved an average score of 76.7, ranking among the leading open-source language models and outperforming SmolLM3-3B and OLMo-3-7B. Trained on AMD Instinct MI300X and MI325X GPUs using the ROCm software stack, Instella-MoE supports 64K token context length. AMD is publicly releasing all model weights, training configurations, data distributions, intermediate checkpoints, and inference code to advance open AI model research.
View Source
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.

Related News

3h ago
AMD Venice CPU Outperforms Nvidia Vera by 20% in Performance, 2.2x Higher Throughput
17h ago
Kimi K3 Outperforms Nemotron 3 Ultra With 2.8 Trillion Parameters, SemiAnalysis Questions Nvidia's Committee Model
22h ago
AMD Unveils Venice 2nm CPU, MI455X GPU, and Helios System on July 23
07-24 01:40
AMD CEO Su Zifeng States Support for Open-Source AI Models on Thursday
07-24 01:37
AMD Unveils Ryzen AI Embedded X100 Series With 16 Zen 5 Cores for Robotics and Edge AI
In-Depth Analysis

Lisa Su Announces Full-Scale Mass Production of Helios AI Racks, 14 Taiwan Supply-Chain Related Stocks Disclosed

Market Whisper07-24 03:11

Alibaba Cloud Zhenwu M890 deploys Qwen3.8, becoming China’s first super node with over 2 trillion parameters

Market Whisper07-24 02:54

AMD Unveils MI455X AI Accelerator, HBM4 Memory Speed Up to 2.9x vs. the Previous Generation

Market Whisper07-24 02:33
Comment
0/400
No comments