Ant Group open-sources Bai Ling large model Ling-2.6-flash
Ant Group’s BaiLing team has officially open-sourced its newest large language model, Ling-2.6-flash. Alongside the standard release, multiple quantized variants—including BF16, FP8, and INT4—are now available, offering global developers greater hardware flexibility and significantly reducing the barriers to AI deployment.
Boasting 104 billion total parameters with 7.4 billion active parameters, Ling-2.6-flash is designed for high performance. Initially tested anonymously on major international benchmarks, the model underwent extensive optimization based on community feedback, particularly improving Chinese-English switching capabilities and code generation accuracy.

Major Gains in Inference Efficiency
Technically, Ling-2.6-flash features an advanced hybrid linear architecture that maximizes computational power. On standard H20 GPU setups, it achieves inference speeds of up to 340 tokens per second, delivering throughput that surpasses many industry competitors.
Beyond raw speed, the model excels in resource efficiency. Evaluations indicate that for tasks of comparable complexity, Ling-2.6-flash uses only one-tenth the tokens of similar-sized models, substantially lowering long-term operational costs for businesses.
Optimized for Intelligent Agents
Addressing the growing demand for AI agents, Ant Group has enhanced the model’s specialized capabilities. It demonstrates robust logical execution and high task success rates, whether handling complex tool calls or executing long-chain planning scenarios.
The model is now accessible on leading open-source platforms like Hugging Face and ModelScope. Through this comprehensive open-source strategy, Ant Group aims to empower developers across various industries to explore new frontiers in large-scale AI applications while maintaining strict data privacy standards.
Related article
South Korea Breaks Ground on National AI Computing Center, Investing 2.5 Trillion Won with 2028 Target
South Korean outlet EtNews reports that groundbreaking for the Korea AI Computing Center (KOACC) took place on August 3 at the Solar City data center park in Sunan, Jeollanam-do. Backed by a total investment of 2.5 trillion KRW (roughly 11.838 billio
Six Tech Giants Back Linux Foundation With $12.5M to Tackle AI Vulnerability Noise
To tackle the flood of low-quality security reports produced by AI automation tools, six major tech companies—Anthropic, Amazon (AWS), GitHub, Google, Microsoft, and OpenAI—have collectively contributed $12.5 million in funding to Linux Foundation in
Musk Considered Leaving OpenAI to His Kids as Altman Testifies
This morning, OpenAI CEO Sam Altman took the stand to address former co-founder Elon Musk’s lawsuit challenging the company’s corporate structure.When asked about Musk’s claim that other founders “stole a charity” by launching a for-profit subsidiary
Related Special Topic Recommendations
Comments (0)
0/500
Ant Group’s BaiLing team has officially open-sourced its newest large language model, Ling-2.6-flash. Alongside the standard release, multiple quantized variants—including BF16, FP8, and INT4—are now available, offering global developers greater hardware flexibility and significantly reducing the barriers to AI deployment.
Boasting 104 billion total parameters with 7.4 billion active parameters, Ling-2.6-flash is designed for high performance. Initially tested anonymously on major international benchmarks, the model underwent extensive optimization based on community feedback, particularly improving Chinese-English switching capabilities and code generation accuracy.

Major Gains in Inference Efficiency
Technically, Ling-2.6-flash features an advanced hybrid linear architecture that maximizes computational power. On standard H20 GPU setups, it achieves inference speeds of up to 340 tokens per second, delivering throughput that surpasses many industry competitors.
Beyond raw speed, the model excels in resource efficiency. Evaluations indicate that for tasks of comparable complexity, Ling-2.6-flash uses only one-tenth the tokens of similar-sized models, substantially lowering long-term operational costs for businesses.
Optimized for Intelligent Agents
Addressing the growing demand for AI agents, Ant Group has enhanced the model’s specialized capabilities. It demonstrates robust logical execution and high task success rates, whether handling complex tool calls or executing long-chain planning scenarios.
The model is now accessible on leading open-source platforms like Hugging Face and ModelScope. Through this comprehensive open-source strategy, Ant Group aims to empower developers across various industries to explore new frontiers in large-scale AI applications while maintaining strict data privacy standards.
South Korea Breaks Ground on National AI Computing Center, Investing 2.5 Trillion Won with 2028 Target
South Korean outlet EtNews reports that groundbreaking for the Korea AI Computing Center (KOACC) took place on August 3 at the Solar City data center park in Sunan, Jeollanam-do. Backed by a total investment of 2.5 trillion KRW (roughly 11.838 billio
Six Tech Giants Back Linux Foundation With $12.5M to Tackle AI Vulnerability Noise
To tackle the flood of low-quality security reports produced by AI automation tools, six major tech companies—Anthropic, Amazon (AWS), GitHub, Google, Microsoft, and OpenAI—have collectively contributed $12.5 million in funding to Linux Foundation in
Musk Considered Leaving OpenAI to His Kids as Altman Testifies
This morning, OpenAI CEO Sam Altman took the stand to address former co-founder Elon Musk’s lawsuit challenging the company’s corporate structure.When asked about Musk’s claim that other founders “stole a charity” by launching a for-profit subsidiary





Home






