yamifyafrica

-Infra: Kubernetes + NVIDIA device plugin; 20× Jetson Nano Dev Kits

-Inference: Ollama / llama.cpp (quantized models ≤7B); token streaming (SSE/WebSocket); autoscaler driven by request queue depth + Jetson tegrastats GPU load

-Cold starts: warm-pool containers with pre-loaded quantized models (to avoid long load times on 4 GB memory)

-Networking: Envoy ingress; TLS.

-Observability: Prometheus/Grafana; structured logs; tracing.

-Billing: pay-as-you-go; mobile money (M-Pesa/Airtel); per-token + per-GPU-hour meters.

-Data: in-region storage; encrypted; no training on customer data.

-Limitations: fewer regions vs AWS; GPU supply fluctuates; docs still early.

-Roadmap: more African regions, spot-GPU pricing, fine-tune jobs.

-Ask: brutal feedback on scaling strategy + CLI UX.

Hi HN! We’re Yamify, building plug-and-play AI infrastructure for African businesses. Small businesses can automate WhatsApp customer support, banks can detect fraud, and law firms can extract insights from documents. Platform runs on local GPU infrastructure, deploys in minutes, and scales seamlessly. We’d love your feedback: usability, new AI tools you’d like to see, and how to make it easier for small teams to onboard.

Techcabal : https://techcabal.com/2025/08/13/yamify-raise-100k-pre-seed/

Techpoint: https://techpoint.africa/brandpress/ex-silicon-valley-cloud-...