3x DGX Spark cluster runs GLM-5.3-Flash locally behind a proxy, 1.75M tokens/day at 119W
Teknium · x · 2026-10-16
Developer Ivan Fioravanti demonstrated a fully local AI workflow: a 3-node DGX Spark cluster (works with Apple Silicon too) running GLM-5.3-Flash (EXL3 quantized) behind a proxy that balances calls, powering a Hermes Agent. Teknium amplified it as "unbelievable power".
The sparkDash dashboard screenshot shows 385GB unified memory across nodes, 51 tok/s decode and 1,156 tok/s prefill, 119W fleet power, 1.75M tokens generated in a day, and live 80°C thermal throttling events — a concrete proof-of-concept for serving open models to agents on consumer hardware.
More from coding & agent
- ERP•AI launches headless SaaS with $0 seats that bills machines: $1 buys 4,000 record writes — rohanpaul_ai · 2026-10-16
- FDE-Gym benchmark shows huge gap on real AI delivery tasks: top model scores 0.563 — DeepLethe · 2026-10-16
- Vibe-coded dashboard leaked franchise financials before anyone logged in — shauntrennery · 2026-10-16
- Fintech HR built a sourcing agent on 60,000 past applicants — 30 qualified candidates in a month — G0NZ0BOY · 2026-10-16
- Orchestrating a 100-image portrait of humanity for aliens with ChatGPT, Argon and p5.brush — dx8xb · 2026-10-16
- Builder's one rule for trusted desktop agents: read freely, but sending, deleting, buying always ask first — No_Fan5310 · 2026-10-16