DeepSeek v4.1 Flash 1017 Original weights royal rumble!
This is a AI post classified by AGK Intelligence as AI infra & evals (a model release), kept by the AI Radar because it carries real work, not commentary.
DeepSeek v4.1 Flash 1017 Original weights royal rumble! Engine (latest version from sources used): - mlx-serve by @ddalcu on Apple Silicon - TensorFold (@MiaAI_lab recipe) on DGX Spark My personal ranking is: 🥇 DGX Spark 🥈 2 x M3 Ultra 🥉 1 x M3 Ultra On decode side M3 Ultra wins, but on prefill there is no match. Clearly I bet things change completely adding M5 Ultra in the arena. So I think 1 M5 Ultra could be better than 4 x DGX Spark in real usage, but the pro on DGX is CUDA. Enjoy detailed results and feel free to ask anything, preparing two new benchmarks to push these machines to t
Posted by Ivan Fioravanti (44.8k followers) 2 h ago · 12 likes · 2.3k views · view the original post on X. Kept by the AI Radar as AI infra & evals.
More AI work like this
- The new GLM-5.3-Flash recipe on 2× DGX Spark — now with the cache fix. — @jmurillocode
- You would think that there's a trade-off between speed and accuracy when it comes to… — @AdamHoltererer
- 太卷了吧！OpenDesign 这波是不是疯了？ — @NFT_Chen
- Guess the model that delivers this cloud TPS? — @wrldsuksgo2mars
- 💥我靠！NVIDIA 直接把 Kimi K3.1 Pro 免费开放了！ — @NFT_Chen
- nice: https://www.linum.ai/field-notes/pjit-21k — @victormustar
- Turning intelligence into measurable business outcomes. — @alibaba_cloud
- Feature preview for Sushi 🍣 1.5.1 - you can set your own thinking tokens limit to any… — @Beamsters1
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. 65.7k 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 13:30 UTC. Full method.