Someone got DeepSeek-V4.1-Flash running at 38.2 tps on an AMD Strix Halo. 🤯
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Someone got DeepSeek-V4.1-Flash running at 38.2 tps on an AMD Strix Halo. 🤯 No multi-GPU server, just a single Ryzen AI Max+ 395 with 128GB unified memory. why should I care? ... because this model is enormous Setup 🧠 552B backbone parameters 💾 ~196B additional Engram parameters 🔥 16B active during decoding 🖥️ AMD Ryzen AI Max+ 395 🎮 Radeon 8060S integrated GPU 💾 128GB unified memory 🐧 Linux + ROCm 7.x The secret? YES! You are correct, new inference engine!! A new open-source inference engine called libosmos. Developer-reported benchmarks using Unsloth's UD-IQ1_S quantization: ⚡ 38.2 tps
Posted by David Hendrickson (12.7k followers) 1 h ago · 30 likes · 2.1k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- 想在自己电脑上玩 AI 生图，开源项目 Qwen Image Local 可以看看。 — @bkdgiffug
- Hermes on Top for Reliability; the metric I personally value most when running dozens of… — @PixelRainbowNFT
- Congrats to the SGLang team @sgl_project and @radixark on the amazing Day-0 Kimi K3.1… — @SemiAnalysis_
- And yes, they do not highlight their own row, those are best results. It is good at… — @teortaxesTex
- 前两天刚写过一篇文章介绍 agent-desktop，今天看 Star 数又涨了不少，已斩获 16000+ Star！ — @GitHub_Daily
- Fun Easter egg — @AdamHoltererer
- Listen to Ultralytics blog articles on the go! 🎧 — @ultralytics
- when you connect Mnemos to your ChatGPT, Claude, Grok, etc. you get your own Notebook.… — @RileyRalmuto
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. 31.9k 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 2026-11-06 03:02 UTC. Full method.