A single RTX 5090 reportedly hit 390 tps running Qwen3.8-Flash-Next on a brand-new…
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.
A single RTX 5090 reportedly hit 390 tps running Qwen3.8-Flash-Next on a brand-new inference engine. Peak? 452 tps Here is the setup 🧠 Qwen3.8-Flash-Next 🔥 125B total / 6B active 🎮 NVIDIA RTX 5090 32GB 💾 128GB DDR5 system RAM 🪟 Windows 11 📚 256K configured context ⚙️ INT8 KV cache Results (decode) 🚀 Infernix + DFlash2 + Q2 → 390 tps ⚡ Strata + MTP + Q2 → 348 tps ⚡ Infernix + native MTP → 304 tps 🟢 NVFP4 configuration → 209 tps 🔵 Qwen FP8 configuration → 60 tps That is a 6.5× difference between the fastest and slowest reported configurations on the same GPU! DAMN! How? Brand new Infernix!
Posted by David Hendrickson (12.8k followers) 1 h ago · 29 likes · 1.6k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- 在别人网站上看到一个很顺滑的动效，丢给 Agent 照着做，它做一遍就说好了，一对比节奏和缓动全不对。 — @GitHub_Daily
- 一张特别惊艳的 AI 图摆在眼前，提示词却不知道从哪儿下手？ — @bkdgiffug
- Meet CaptchaKraken v1.2 GGUF: a quantized image-text-to-text model built on Qwen3.5-9B… — @HuggingModels
- BREAKING: — @guilleflorvs
- ye diwali Voice AI wali — @akshay81844
- FlashAlign 1.2 ⚡ — @Kurcide
- Top 7 agent profile spends on one of 7 Hermes devices in my fleet. Default = my Chief of… — @PixelRainbowNFT
- Grok Build v1.0.78 is out with a few practical updates. Standouts include @ file chips… — @blankspeaker
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 05:57 UTC. Full method.