llama.cppで起動したMiMo-V2.6-Distill-Qwen-9Bにやらせた。ラーメン屋ベンチの結果です。動画をご査収ください。
This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
llama.cppで起動したMiMo-V2.6-Distill-Qwen-9Bにやらせた。ラーメン屋ベンチの結果です。動画をご査収ください。 あり得ない速度で、Q4_K_M GGUFに量子化されてるやつあったので、それでやりましたん。 リプライに貼っとくよぉ～。 Q4量子化後→5.63 GB<軽ｽｷﾞｨ MCode画面表示: 約 93.8 tok/s llama-server単独生成: 約 115〜119 tok/s 2ジョブ同時実行時: 約 94〜95 tok/s 画像はPixabay API渡して取ってこさせてます。 GPU: NVIDIA GeForce RTX 4090 24GB CPU: AMD Ryzen 9 7950X3D メモリ: 64GB モデル: MiMo-V2.6-Distill-Qwen-9B Q4_K_M GGUF ハーネス：Minimax Code
Posted by StudioYebisu (1.9k followers) 1 h ago · 6 likes · 588 views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: mimo-v2.6-distill-qwen-9b.
More AI work like this
- Meet decider-2b: a 2B parameter decision model that runs in ONE pass. No chains, no… — @HuggingModels
- Xiaomi’s MiMo V2.6 Pro looks like a contender for the best new model to run locally. — @plotarmordev
- Here's a model that shouldn't be overlooked! — @mr_r0b0t
- I let Kev play Dwarf Fortress — @TelepathicPug
- the open frontier intelligence list keeps on growing. — @arjunkocher
- Qwen Image 2.1 Is OPEN WEIGHTS… Nano Banana 2 at HOME ! https://youtu.be/6teCD4Kq4wA — @Tech2Wild
- Yesterday you could already make realistic images locally with Krea 2 on an RTX card. — @yume_arasaki
- 60.4 Qwen 3.8 Flash Next 1 spark — @TechMDAI
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 40.6k posts from 5k X accounts over the last 14 days, 1.7k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 00:34 UTC. Full method.