Ling-3.0-flash Open Weights Released with BF16 and FP8 Versions

aftahi_ai · x · 2026-08-05

AntLingAGI has officially released the open weights for Ling-3.0-flash.

Both BF16 and FP8-quantized versions are now available, allowing developers to choose the option that best fits their hardware, performance requirements, and deployment needs for fine-tuning and optimization.

Related event: Ant Group open-sources Ling-3.0-flash: 124B params, only 5.1B active(11 posts)→

Original post →

More from Models

Models channel →