Local AI doesn't seem to have advanced much in the past few months compared with hosted models. Are we going to have Opus-5.5 available locally 6 months from now?
Local AI is good enough for a startup. A 10-person startup built its own 128GB-VRAM AI server for $18,000.
One Threadripper box sitting locally with
🎮 4× Radeon AI PRO R9700 32GB
💾 128GB total VRAM
🧠 Qwen3.8 + DeepSeek V4 Flash
👥 16 concurrent AI sessions
And they're actually pushing it.
Qwen3.8-Flash-Next with 16 simultaneous sessions:
📚 48K context/user
⚡ 538.5 tps aggregate decode
At 128K context per user
⚡ 365 tps aggregate decode
The GPUs are even undervolted to under 210W each.
Link in ALT
Local authorities in Arlington, Virginia, sued the US Department of Interior and National Park Service, seeking to block President Trump's proposed triumphal arch