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 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.
⚔️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) 1 days ago · 14 likes · 2.3k 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.