MiniMax-M3.1-Flash on a Mac Studio vs GLM-5.3-Flash on 2 DGX Sparks.
This is a dev post classified by AGK Intelligence as Other (a launch), kept by the Dev Radar because it carries real work, not commentary.
Two LLMs go to war! MiniMax-M3.1-Flash on a Mac Studio vs GLM-5.3-Flash on 2 DGX Sparks. Mac Studio M5 Ultra: MiniMax-M3.1-Flash Ash's TensorFold 1.2.1 recipe MLX mix256k weights, ≈3.8 bpw average (mixed) 2x DGX Spark: GLM-5.3-Flash Mia's TensorFold recipe, commit bf5f945 EXL3 4 bpw Today's rules: the only way to win is to destroy the enemy base. Two towers per side at most. From minute 10 both sides get unlimited resources. This is the strategy game I'm building. It runs in real time (this match at half speed). Both models think before they act, no human input. Two AI casters (Drama 3
Posted by Niklas (2.8k followers) 1 days ago · 173 likes · 21.6k views · view the original post on X. Kept by the Dev Radar as Other.
More dev work like this
- 就在刚刚，百度文心终于出手了，把自家基座模型文心 5.5 Flash Base 开源。 — @GitHub_Daily
- 🚀Baidu just open-sourced ERNIE-5.5-Flash-Base — @Chinazhidx
- @Baidu_Inc released ERNIE 5.5 Flash Base. — @javierbits
- JUST IN: @VerneRobotics released V0.5, an open-weight model for industrial robots. — @IlirAliu_
- 读英文 PDF，最耗神的往往不是内容本身，而是术语和长句总把节奏打断。 — @bkdgiffug
- Nanjing Iron and Steel (NISCO) has 300+ AI models, 25 business agents, and 1,000+… — @Huawei
- 搭 3D 场景时缺几个小道具，桌上的杯子、墙角的椅子，自己建模太费时间，去素材站翻半天也不一定有合适的。 — @GitHub_Daily
- 2 minutes of continuous AI video with spoken dialogue, generated at home on two NVIDIA… — @majewskizby
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. 31.7k posts from 5k X accounts over the last 21 days, 9.4k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 11:17 UTC. Full method.