Single-Tower High-Performance Rig
While most people drop thousands of £GBP on a depreciating Audi Q3 that loses value the moment they drive it off the lot (or worse, they lease it), I'd rather sink that money into something that can actually produce interesting things. This machine currently runs 70B+ parameter models locally and processes terabyte-scale microscopy datasets. The full build-out to three GPUs and 1TB of RAM will generate value every day and stay relevant as I upgrade components.
The core philosophy here is modularity without compromise. The Threadripper 7970X gives me 48 PCIe 5.0 lanes, meaning I can run three flagship GPUs at full x16 bandwidth without needing £GBP thousands more on a dual-socket EPYC or enterprise Xeon platform. The ASUS Pro WS TRX50-SAGE has IPMI and ECC support, so this isn't just a gaming rig with delusions of grandeur—it's production-grade infrastructure.
This started as a microscopy research platform. I needed something that could crunch through days of high-resolution imaging data while simultaneously running LLM inference for automated experimental workflows. Turns out, the Venn diagram of "can process microscopy data" and "can run massive language models" is just "absurdly powerful computer."
ECC memory isn't negotiable. When you're running multi-day experiments or training on scientific data, a single bit flip can corrupt everything. The 128GB DDR5 ECC setup expands to 1TB because why set artificial limits?
The 96TB ZFS pool means I can stop worrying about cloud storage costs and actually work with real datasets locally. Checksumming, snapshots, data integrity—all the things you want when your data represents months of work.
The RTX 6000 Blackwell (96GB VRAM) is cutting-edge enough to stay relevant as models get bigger, and when I need more, I'll just add two more GPUs. 288GB total VRAM in a single tower. No racks, no datacenter, no monthly AWS bills making me cry.
| Sub-system | Component | Rationale |
|---|---|---|
| CPU | AMD Threadripper 7970X | 32 cores, 48 PCIe 5.0 lanes. |
| GPU | NVIDIA RTX PRO 6000 96GB | Blackwell architecture for large-scale compute. |
| RAM | 128 GB DDR5-4800 ECC | RDIMM; Expandable up to 1TB. |
| NVMe OS | Crucial P2 1TB | Dedicated OS drive. |
| NVMe Scratch | Samsung 9100 Pro 8TB | 8TB scratch storage for active datasets. |
| Bulk Storage | 96TB ZFS Pool | 4x Seagate IronWolf Pro 24TB drives. |
| Motherboard | ASUS Pro WS TRX50-SAGE | IPMI and ECC support. |
ColPali Research Engine
A containerized Vision-RAG pipeline that bypasses traditional OCR to perform visual document retrieval directly on document images.
./manage_env.sh
| Stack | Technology | Implementation |
|---|---|---|
| Environment | CUDA 12.6.2 | PyTorch Nightly for sm_120 support. |
| Retriever | ColPali v1.2 | 200 DPI multi-vector indexing. |
| Reader | Qwen2-VL-7B | Visual reasoning with grounding enforcement. |
| Storage | NVMe Volume Mount | Direct access to 8TB scratch NVMe. |