Autonomous Computer: $26K Dual RTX 5090 Workstation Targets Local Frontier Models
dee_hw · x · 2026-08-11
A user shared details about the Autonomous Computer, a dual-GPU AI workstation priced from $26,100. The device is designed to run frontier models locally (e.g., DeepSeek V4 Flash) at impressive speeds up to 300 tok/s, aiming to free users from per-token API billing and cloud privacy concerns.
The base configuration features two RTX 5090 GPUs, offering 64GB of VRAM and 210 TFLOPS of FP32 compute, with options to upgrade to RTX PRO 6000 Blackwell. The system is housed in a CNC-milled aluminum chassis and includes dual PCIe 5.0 x16 risers and a 2000W power supply. The pitch emphasizes total ownership of model weights, physical data privacy, and the ability to fine-tune models on proprietary data.
More from Infra
- Nemotron 3.5 Hits 4,694 tok/s with 64 Concurrent Generations on a Single GH200 — pcuenq · 2026-08-12
- NVIDIA's NeMo Switchyard Cuts Coding Agent Costs by 59% and Runtime by 32% in Ramp Test — sudoraohacker · 2026-08-12
- SD Video Optimization: CK Cuts Generation Time to 473s, but Degrades Prompt Adherence — switch2stock · 2026-08-12
- Muse Glimmer 30B Hits 25 tok/s In-Browser on M4 Max via Custom WebGPU Kernels — xenovatech · 2026-08-12
- Developer asks OpenAI about running ML experiments on basement GPUs — daniel_mac8 · 2026-08-12
- LMSYS introduces Unified Radix Cache: one tree for hybrid model prefix caching — ying11231 · 2026-08-12