Gate News message, April 29 — Ant Group’s Ling-2.6-flash model weights are now open-sourced, having previously been available only via API. The model features 104 billion total parameters with 7.4 billion activated per inference, a 256K context window, and MIT licensing. BF16, FP8, and INT4 precision versions are available on HuggingFace and ModelScope.
Ling-2.6-flash introduces hybrid linear attention improvements over Ling 2.0, upgrading the original GQA to a 1:7 MLA plus Lightning Linear hybrid architecture combined with highly sparse MoE. Inference efficiency significantly exceeds comparable models: peak generation speed reaches 340 tokens/s on 4x H20 GPUs, with prefill and decode throughput approximately 4x higher than comparable open-source models. Agent-related benchmarks show strong performance: BFCL-V4, TAU2-bench, SWE-bench Verified (61.2%), Claw-Eval, and PinchBench achieve or approach SOTA levels. Across the full Artificial Analysis benchmark suite, total token consumption is only 15 million. On AIME 2026, the model scored 73.85%.
Ant Group’s official website also lists Ling-2.6-1T (trillion-parameter flagship version) and Ling-2.6-mini (lightweight version), though as of publication, their weights remain unreleased on HuggingFace, with only the flash series available for download.
Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to
Disclaimer.
Related Articles
X (Twitter) ushers in its biggest ad platform upgrade in 20 years, with xAI involved; AI semantic targeting becomes the core
X announced that it will roll out the largest advertising platform overhaul in 20 years starting in April 2026, rebuilding the underlying technology and combining it with xAI. The new platform will focus on AI-driven performance optimization and semantic and contextual advertising to improve operational convenience and ad placement control. Its goal is to turn advertising into real-time commercial signals in context, and to serve as X’s business engine within the X ecosystem in line with its Everything App strategy.
ChainNewsAbmedia14m ago
OpenAI-Backed 1X Opens 58,000-Sq-Ft Factory in California, Targets 10,000 Robots in First Year
According to Bloomberg, 1X Technologies, an OpenAI-backed robotics startup founded in Norway, has opened a 58,000-square-foot manufacturing facility in Hayward, California, aiming to lead in mass-producing consumer-grade humanoid robots.
The facility is expected to produce 10,000 robots in its
GateNews2h ago
White House Drafts AI Policy Memo Directing U.S. Agencies to Use Multiple AI Providers on April 30
According to sources cited by PANews on April 30, White House officials are drafting a broad artificial intelligence policy memo that directs U.S. government agencies to adopt multiple AI service providers and avoid reliance on a single vendor. The memo also requires all AI companies contracted
GateNews3h ago
China's Cyberspace Administration Launches 4-Month Campaign to Curb AI Application Chaos on April 30
According to CCTV News, China's Cyberspace Administration launched a nationwide four-month campaign on April 30 to address AI application chaos. The initiative, deployed across two phases, targets issues including missing model registrations, inadequate platform safety and review capabilities,
GateNews3h ago
Forefront Tech Completes $100M IPO Pricing, Nasdaq Listing Under Code FTHAU
According to ChainCatcher, special purpose acquisition company Forefront Tech completed a $100 million IPO pricing on April 30 and will list on Nasdaq under ticker symbol FTHAU. The company plans to use the proceeds to pursue merger and acquisition opportunities in blockchain, fintech, artificial in
GateNews4h ago
Anthropic Claude Code Overcharged User $200.98 Due to Billing Bug, Initially Denied Refund Before Full Compensation
According to monitoring by Beating, a billing bug in Anthropic's Claude Code service caused a Max 20x subscriber to be overcharged $200.98 in extra usage fees while only using 13% of their monthly quota. The bug was triggered when a user's git repository commit history contained the uppercase
GateNews5h ago
