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.
More from Models
- Why are sub-15B open models so rare now? Labs seem to have settled on 24-27B minimum — Hot_Example_4456 · 2026-10-16
- User spots model openly generating "ideal responses" to train other models — liminal_bardo · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Gemma 4 31B QAT on one 24GB card: 46 tok/s plain, ~80 with draft model on RTX 4090 — Subject_Poet_3861 · 2026-10-16
- JevBench v1.7.46 leaderboard: new d1-ultra tops 32 API systems at 76.1 composite — airesearch12 · 2026-10-16
- Team of 5 mulls dropping ChatGPT Pro for Business as OpenAI quota parity stays unclear — bettercallfool · 2026-10-16