AMD Localmaxxers are getting serious about inferencing. 🤯
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.
AMD Localmaxxers are getting serious about inferencing. 🤯 Someone just hit 1,426 tps running Qwen3.8-27B on 4x AMD Radeon GPUs. And it's running on a single ~$18,000 workstation. 👀 Here's the hardware setup 🔴 4× AMD Radeon AI PRO R9700 💾 32GB VRAM per GPU 🔥 128GB total VRAM ⚡ 210W power limit per GPU 🧠 ASUS TRX50 SAGE motherboard ⚙️ Tensor parallelism across all 4 GPUs 💾 BF16 KV cache 🚀 Multi-token prediction (MTP) Now look at the developer-reported benchmarks. Qwen3.8-27B FP8 w/8 concurrent users 📥 Prefill → 7,025 tps ⚡ Decode → 813.9 tps Qwen3.8-27B MXFP4 w/16 concurrent users 📥 Prefill
Posted by David Hendrickson (12.8k followers) 48 min ago · 10 likes · 907 views · view the original post on X. Kept by the AI Radar as AI infra & evals.
More AI work like this
- The enterprise AI bottleneck has moved from models and GPUs to the data path. — @Dell
- We evaluated Nexus on 7 benchmarks and 1,222 tasks. It defines the Pareto frontier. — @FireworksAI_HQ
- There is a 560B model running with its full 1M context on 2x DGX Sparks by @andersjw_. — @plotarmordev
- 免费GPT的API，手快有手慢无 — @mylifcc
- TensorFold 1.2.4 is out. 🚀 — @ashxhart
- AWS is making it easier to run several smaller models on the same GPU. — @markfenner
- The @nvidia Jetson Orin Nano is back in the lab. — @jmurillocode
- We want to sponsor Rust maintainers and open-source projects across web development,… — @encoredotdev
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. 65.2k posts from 5k X accounts over the last 14 days, 10.6k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 16:45 UTC. Full method.