Home AI Server — Punkstation Pro - 88 GB VRAM - EPYC

The Punkstation on a server-grade platform: a consumer RTX 4090 paired with a driver-unlocked NVIDIA CMP 170HX (64 GB HBM2e) — 88 GB of aggregated VRAM — on a single-socket AMD EPYC board with ECC memory, IPMI remote management and four PCIe 4.0 ×16 slots to grow into. Not the budget desktop — a robust, expandable machine, built and configured for maximum performance. Available as a quiet tower or a rack-mount server. 88 GBaggregated VRAM (24 + 64) EPYCserver platform · ECC · IPMI 2 → 4GPU slots (room to expand) What it's for Same aggregated-VRAM strengths as the Punkstation, on hardware that lasts and scales. VRAM is aggregated, not pooled — the two cards are independent memories, so it's at its best on video and image generation, large mixture-of-experts models that fit one card, and mixture-of-agents / multi-model pipelines. The RTX 4090 drives the desktop and fast image generation; the 170HX's 64 GB carries the big model. The EPYC platform adds ECC memory, out-of-band IPMI management, more PCIe lanes and NVMe, and a clear upgrade path to the 4× 170HX build. Image generationMixture-of-agentsVideo generationMoE reasoning Validated: Qwen3 35B-A3B (mixture-of-experts, W8A8, compiled) runs entirely in the 170HX's 64 GB with no offload at ~140 tokens/s single-stream (and ~3,270 tok/s across a 48-request batch) — faster than a 7B dense model while reasoning coherently. Video / image: generation models can't be split across cards — each fits one GPU. The 170HX's 64 GB hosts large diffusion and video models at high resolution and batch; the 4090 gives fast SDXL/Flux-class image generation. Run both in parallel for concurrent jobs. Specification Component Detail Accelerator 1 NVIDIA GeForce RTX 4090 · 24 GB GDDR6X · drives display + fast single-card work Accelerator 2 NVIDIA CMP 170HX · 64 GB HBM2e (modified, driver-unlocked, compute-only) Total VRAM 88 GB aggregated (24 + 64), both fully accessible CPU AMD EPYC (Rome / Milan, SP3) — model configured to order Mainboard Single-socket EPYC server board · 8-channel DDR4 ECC · 4× PCIe 4.0 ×16 · onboard graphics + IPMI/BMC remote management Memory DDR4 ECC, octa-channel — configurable (128 GB typical) Storage M.2 NVMe (up to 3× PCIe 4.0 ×4) Networking Dual 2.5 GbE + dedicated IPMI remote-management port Power Uprated PSU sized to the build Chassis Quiet desktop tower — or rack-mount server (choose above) Operating system Ubuntu, NVIDIA drivers + CUDA pre-configured, compiled/cudagraph runtime tuned Assembly Built, burned-in and validated at maximum performance before dispatch Please read before ordering ⚠ Driver-unlocked card. The CMP 170HX is a compute card unlocked to full speed outside NVIDIA's specification. The configuration is confirmed working and ships validated, but the 170HX carries no manufacturer warranty — Kentino covers the build and the standard components; the 170HX is supported on a best-effort basis. The 170HX is compute-only (no display) — the RTX 4090 (or onboard BMC graphics) drives the console. The 170HX links at PCIe 2.0 (×4 standard, ×16 mod available) — limits host↔device transfer, not resident-model inference. Ordering Price in preparation — request a quote. Choose Tower or Server (rack) above. Lead time 10–28 days. Prices are EUR ex-VAT. Bespoke CPU / memory / storage configured to order.