Brutech · Workstations

Brutech | Edison

Edison Class
R 269,999.00
Tax included.Shipping calculated at checkout
⚡ Finance from / month × 24 · View options →
▾ MORE PAYMENT OPTIONS
Flexible payments from R 44,999.83

Pay over 2-6 interest-free instalments with Stitch Pay Later

We accept

Visa Mastercard Apple Pay Google Pay Capitec Pay Stitch Pay Later
// Item Lore

We built the Edison for the professional who needs everything the Darwin offers with more GPU power to match.

Named after Thomas Edison a scientist defined by relentless iteration and improvement the Edison is the Darwin's natural evolution. The same AMD Ryzen Threadripper 9960X with 24 cores and 48 threads of Zen 5. The same ASUS Pro WS TRX50-SAGE WIFI professional platform. The same 128GB DDR5, 4TB NVMe primary storage, 60TB additional storage, and 1600W platform. The same POP!_OS Linux pre-installed for CUDA, ML, and scientific computing workflows. The same 5-year warranty.

One difference. The RTX 5080 16GB replaces the RTX 5070 Ti significantly more CUDA cores, more GPU compute throughput, and more headroom for the workloads where GPU performance is the bottleneck. Hand-assembled by us in Secunda. Zero bloatware.

Research Loadout Edison Class
Graphics NVIDIA GeForce RTX 5080
Processor AMD Ryzen Threadripper 9960X
Motherboard ASUS Pro WS TRX50-SAGE WIFI
Memory 128GB DDR5
Storage 4TB NVMe60TB HDD
Cooling Arctic Freezer 4U-M Rev. 2
Power 1600W Gigabyte 80+Gold Modular PSU
Case Fractal Design Meshify 3 XL
OS POP_OS! Linux
Warranty 5-Year Limited Warranty
Origin Hand Assembled in Secunda
🛡️ 5-Year Warranty 📦 Ships Nationwide⚡ Built in Secunda 💬 Real PC Builder Support
1
🔬 Deploy to your research rig
Loading...
Loading...
Loading...
Loading...
// Accepted
Brutech | Edison
R 269,999.00
// Lab stress-tested
Compute Readiness
Stress-tested across demanding compute pipelines
Edison Class
AI LLM 30B MODERATE
PERFORMANCE25 tokens/s
NOTESCPU Inference (16GB VRAM)
Blender BMW HIGH
PERFORMANCE21s
NOTESGPU Render
Data Science STRONG
PERFORMANCEVery Fast
NOTES8-Ch DDR5 128GB
Premiere 4K Export HIGH
PERFORMANCE1m 18s
NOTESH.265 Output
Cinebench R24 nT STRONG
PERFORMANCE5,600 pts
NOTES24-Core Score
Virtual Machines STRONG
PERFORMANCE16x Concurrent
NOTESFull Isolation
ML Model Training STRONG
PERFORMANCE11 img/s
NOTESPyTorch GPU
// Darwin and Edison use CPU inference for 30B LLM (16GB VRAM insufficient for Q8 quantisation). Newton through Einstein use full GPU inference. Cinebench nT scores reflect actual core counts: 24C (Darwin/Edison), 32C (Newton), 64C (Hawking/Einstein).