Shanghai AI Lab and SJTU’s LUMIA Lab release NCP-ArchPreview, an open-weight 8.9B…

This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
Shanghai AI Lab and SJTU’s LUMIA Lab release NCP-ArchPreview, an open-weight 8.9B language modell. 📜 Apache 2.0. 🤖 https://modelscope.ai/collections/Shanghai_AI_Laboratory/NCP_ArchPreview 📄 https://modelscope.ai/papers/2609.10715 ⚡ Trained on 5.73T Dolma 3 tokens, it reaches OLMo-3-7B’s final Stage 1 loss with only 51.3% of the tokens, a 1.95× convergence gain. 🏆 Its Stage 1 macro-average rises from 46.59 to 49.04, with +5.99 on GSM8K and +4.28 on HumanEval. 🧠 NCP jointly predicts tokens and a concept sequence at one-quarter the length, then feeds those concepts back to guide generation. 🛠 Do
Posted by ModelScope (15.9k followers) 1 h ago · 16 likes · 882 views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: Ling-3.0-flash-Fin.
More AI work like this
- Meet dQwen3.5-9B-Base: a 9B diffusion language model that blends masked diffusion with… — @HuggingModels
- Meet dQwen3 1.7B Base: a diffusion language model built on Qwen3. Instead of predicting… — @HuggingModels
- Diffusion models aren't just for images anymore. DiffuRefill-1B brings masked diffusion… — @HuggingModels
- Meet Open JEV DeBERTa V3 Large: a text classification model that doesn't just label, it… — @HuggingModels
- One 36B MoE. Six EXL3 releases. GPUs from 8 GB to 96 GB. 🔥 — @ViC305
- NEW UNCENSORED Xiaomi MiMo-V2.6-Flash model you can run locally with Zero refusals. — @0x0SojalSec
- these are the best cheap models right now — @nicdunz
- Qwen-Image-2.1 开放权重后,许可证成了最大的争议点 — @xueyu1125
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 43.9k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 06:32 UTC. Full method.