MiniMax-M3.1-Flash at 3.06 bpw on 2 DGX Sparks vs 1.6-bit experts on one RTX 5090. Only…
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! ⚔️ Round 3 MiniMax-M3.1-Flash at 3.06 bpw on 2 DGX Sparks vs 1.6-bit experts on one RTX 5090. Only one base survives. 2x DGX Spark: MiniMax-M3.1-Flash Ash's TensorFold 1.2.1 recipe Mia's EXL3 quant, 3.06 bpw 171 GB of weights 1x RTX 5090: MiniMax-M3.1-Flash Project Maya v1.1.50 Maya-XS quant, experts ≈1.6 bit 93 GB of weights Maya keeps most experts in the PC's RAM (63 GB) and uses 16 CPU threads next to the 5090. Each engine runs the way its author runs it. Today's rules: the only way to win is to destroy the enemy base. Two towers per side at most. From minute 10
Posted by Niklas (2.8k followers) 8 h ago · 12 likes · 1.7k views · view the original post on X. Kept by the Dev Radar as Other.
More dev work like this
- 彭博终端对个人用户来说，确实贵得下不去手。 — @bkdgiffug
- Nanbeige has released Nanbeige4.3-33B, an open weights model matching Qwen3.8 27B… — @ArtificialAnlys
- 🔥谷歌刚发布 Gemini Omni 1.2 Flash，视频生成能力直接再上一个台阶！ — @NFT_Chen
- Nano Banana Pro V2 is that you 👁️ — @IamEmily2050
- Most blockchains pay for security one way: new token emissions. — @CNPYNetwork
- Ok, é verdade. Lichii é o emulador e está no GitHub (nunca baixe de qualquer outro… — @AkitaOnRails
- Cinetic v1.5 is out! — @LexnLin
- Wio Tracker L2 Pro meets Home Assistant + XiaoZhi AI. — @seeedstudio
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. 31.6k 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 18:08 UTC. Full method.