Ant Ling Team Open-Sources Ling-3.0-tiny: An 8B Parameter MoE Model
tomaarsen · x · 2026-08-11
Following Ling-3.0-flash, the Ant Ling team has officially open-weighted Ling-3.0-tiny.
- Architecture & Parameters: Features a Mixture-of-Experts (MoE) architecture with 8B total parameters and only 1.3B active parameters, designed for extreme inference efficiency.
- Performance: Scores 25 on the Intelligence Index and 16 on the Agentic Index on Artificial Analysis, built for real task execution.
- Formats: Model weights are available on Hugging Face in BF16, FP8, and INT4 precisions to support various deployment environments.
Related event: Ant's Ling Team Open-Sources 8B MoE Model Ling-3.0-tiny(2 posts)→
More from Models
- Claude Increases Lower Bound for Riemann Hypothesis to 67.2% — BoyNextDoor1990 · 2026-08-11
- Google's Gemini Omni Lite reportedly launching soon with focus on video — koltregaskes · 2026-08-11
- GPT 5.6 Sol Halves Coding Costs While Matching Previous Performance — jyangballin · 2026-08-11
- GPT 5.6 Sol Generates Novel Code Solutions, Not Just Memorization — jyangballin · 2026-08-11
- GPT 5.6 Sol Tops ProgramBench, Successfully Rebuilding Complex Programs — jyangballin · 2026-08-11
- Meta Rumored to Release Frontier Open-Weight Model Under Apache License — TimDarcet · 2026-08-11