How I repurposed a £200 datacenter GPU to run large AI models on a gaming PC
By
Oscar Molnar
Master baker tier. Every paragraph earns its place on the tray.
Summary
A tech enthusiast details how they purchased a used Tesla V100 SXM2 datacenter GPU for £200 and adapted it to work in a standard gaming PC alongside an RTX 4080. The project involved sourcing a custom adapter, jury-rigging cooling with jumper wires, and overcoming numerous technical hurdles. The result is a dual-GPU setup with 32GB of VRAM capable of running a 27-billion-parameter local AI model at 32 tokens per second, rivaling commercial models like Claude Sonnet 4.6 on benchmarks.
Key quotes
· 5 pulledI bought a datacenter GPU that doesn't even have a normal PCIe connector, stuck it in my gaming PC with an adapter, and now I have 32GB of VRAM across two GPUs running a 27 billion parameter model at 32 tokens per second.
The whole thing cost me £200.
I already had an RTX 4080. 16GB of VRAM. Good enough for gaming, not good enough for the models I wanted to run locally.
This is a Tesla V100 SXM2 16GB. It was designed for NVIDIA's DGX servers and hyperscaler racks.
I bought a datacenter GPU that doesn't fit in a normal motherboard, macgyvered the fan with jumper wires, and now I'm running a model that ties with Claude Sonnet 4.6 on benchmarks, all for £200.
You might also wanna read
General Compute Launches ASIC-Based Inference Cloud for Faster AI Agent Performance
General Compute is an inference cloud built on ASICs (purpose-built alternatives to Nvidia GPUs) designed specifically for AI inference, not
Product Hunt·1mo ago
Razer Launches Forge AI Workstation for AI Development and Training
Razer, known for gaming hardware, is expanding into AI development hardware with a new Forge AI workstation designed for AI training, infere
The Verge·4mo ago