Mistral Large 4 is now open weight, so let's look inside the model and its architecture…
This is a dev post classified by AGK Intelligence as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
Mistral Large 4 is now open weight, so let's look inside the model and its architecture 👁️ first it's full sparse attention, like V3.2 and GLM 5.X series, KV cache sharing for NoPE layers after layer 35, and indexer sharing on RoPE layers starting at layer 17 (RoPE layers never share the index with NoPE layers) the indexer is classical MLA/DSA with a small tweak, they don't down project q and add a norm on it instead. what is interesting is if we look at the weight of the indexer itself: - indexers are very different from one layer to another, if you look at GLM and DeepSeek you actually see
Posted by elie (26.2k followers) 1 days ago · 575 likes · 28.6k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- 长PDF要是拆成单页再往一块拼，跨页表格和阅读顺序十有八九会乱套，这事你八成也烦过。 — @bkdgiffug
- Local models on Apple Silicon finally feel like a product, not a weekend project. — @PixelRainbowNFT
- GPT 6.1 Terra max vs GPT 6.1 Sol max — @HarshithLucky3
- Asked at the Meetup: "Does sbx run mistral work?" — @ajeetsraina
- Most agents freeze once deployed. — @GoogleCloudTech
- Your $250 GPU can now run a 35B coding model at 50 tokens/sec. — @0x0SojalSec
- Next week we're showing how to build self improving products. — @spenserskates
- Seedance 2.5 US Draft mode is now available on fal — @fal
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. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 22:12 UTC. Full method.