Ling-3.0-tiny is now available as an open-weight model in BF16, FP8 and INT4.
On Artificial Analysis, it scores 25 on the Intelligence Index and 16 on the Agentic Index, with 772 Elo on GDPval-AA v2 and 20.80 on τ³-Banking—built for real task execution. 🧵
Across broader evaluations, Ling-3.0-tiny reaches 71.03 on IMO-AnswerBench, 73.40 on GPQA Diamond, 83.15 on Multi-IF and a 69.54 non-hallucination rate.
It delivers balanced coverage across reasoning, coding agents, instruction following and long-context tasks.
Efficiency is architectural: a 3:1 KDA–MLA hybrid attention stack and 128 sparse MoE experts, with 8 routed and 1 shared expert active per token.
The result is high model capacity with lower per-token compute and a more accessible deployment footprint.
Already running on real hardware:
• DGX Spark FP8: ~100–105 tok/s for one request; ~161 tok/s aggregate for two
• MacBook: local BF16/FP8, with FP8 ~30% faster in sustained generation
• Mac mini: an always-on node for private knowledge, automation and local APIs
mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
attention — The mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
Why it matters
A 7.9B open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → model with 1.3B active parameters and published agentic benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition → scores runs locally on a MacBook or DGX Spark, giving a private, zero-API-cost option for tool-use and retrieval loops.
Read the full thread on X ↗
