New base model. Baidu released a 280B open-weight model that activates only 14B…
This is a AI post classified by AGK Intelligence as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
New base model. Baidu released a 280B open-weight model that activates only 14B parameters. It has a very interesting trick for long-context Local AI and one big catch. Trick? In 37 of its 43 attention layers, it compresses every 128 older tokens into a single cached entry. These are ERNIE-5.5-Flash-Base stats 🧠 280B total / 14B active 📖 Trained from scratch on 33.5 TRILLION tokens 📚 128K training context / up to 1M inference 💾 Official FP8 + BF16 weights 🔓 Downloadable under a custom license To make its context efficient, 37 layers use Heavily Compressed Attention 128 older tokens → 1 ca
Posted by David Hendrickson (12.8k followers) 1 days ago · 21 likes · 1.3k views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- Qwen 4 (unnamed quant) — @loktar00
- 北冥有鱼，其名为鲲。 — @NFT_Chen
- If you want to get started with Local AI but dunno where to start, THIS IS FOR YOU 🚨 — @javierbits
- 💥重磅！Qwen3.8-Flash-Next 量化版炸裂升级：Token消耗直接腰斩50%，准确率暴涨15%！本地32GB丝滑跑通125B级MoE！ — @NFT_Chen
- This could be so cool. — @niklaslenz_ai
- Qwen is teasing a new model — @RoundtableSpace
- 时代变了，以前是token每秒，有人提出了秒每token。。。。 — @mylifcc
- Qwen3.8-Flash-Next GGUFs now run faster with less thinking and less token use. — @UnslothAI
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:05 UTC. Full method.