Ling-3.0-flash debuts with 124B parameters and 5.1B active per token
aftahi_ai · x · 2026-07-27
- AntLingAGI says it has released Ling-3.0-flash, a hybrid-reasoning MoE model aimed at production-scale agents.
- The model uses 124B total parameters with only 5.1B active per token.
- The quote claims it can match or beat the company’s 1T flagship model on most of the benchmarks shown, while using only 1/8 of the total parameters and 1/12 of the active parameters.
- The repost adds that Ling 3.0 Flash is free until August 3, encouraging people to test reasoning, coding, and long-context performance in real workflows.
Related event: Ant Group Releases Ling-3.0-flash Hybrid Reasoning Model(2 posts)→
More from Models
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27
- Kimi K3.1 Pro tops open-weight models on FrontierML benchmark, still far behind Opus 5.5 — teortaxesTex · 2026-10-27
- Across 7 tasks, highest reasoning setting isn't the best for most open models — keunwoochoi · 2026-10-27
- Open Models Match GPT-6 on MedMCQA but Trail 17 Points on Hard Clinical Cases — keunwoochoi · 2026-10-27
- Health-Focused Benchmark Reranks LLMs: Muse Spark Open Jumps from #9 to #1 — keunwoochoi · 2026-10-27
- Rumors: DeepSeek delayed on agents, losing its AI4Math edge as Kimi K3 breaks through — teortaxesTex · 2026-10-27