How to Size a Private AI Deployment (6 Steps · Before You Buy Any GPU)

TL;DR: Skipping any of these 6 steps = 30-60% wasted GPU or 2-3 wasted delivery months. Applies to healthcare / manufacturing / law firm / SOE / finance / cross-border SaaS.

Step 1 · Quantify Peak Concurrency

Peak QPS + parallel long-context sessions + duration distribution. Not average — peak. If unknown, worst case = 2× your best guess.

Sample real numbers from delivered projects: - Tier-3 hospital doctor assistant: ~30 concurrent doctors at peak (morning rounds 8-10am), each session 200-2000 tokens output. See Case 01. - 400+ microservice AIOps: ~5000 alerts/day, peak concentrated in incidents. See Case 14. - 200+ engineer CI/CD: ~50k commits/month, peak on Monday and pre-release. See Case 15.

Step 2 · Freeze p95 Latency Target

Pick before hardware. User pain threshold: - Chat / doctor query: 2-3s p95 - Voice interaction: 800ms p95 - Line-side vision (visual QA): 100ms p95 - Bulk analysis (contract review): 60s batch is acceptable

Latency target directly drives model size cap. 72B at 3s p95 requires ≥ 2×A800 or ≥ 4×4090.

Step 3 · Profile Task Shape

Task shapes have very different infra needs:

Task shape VRAM Throughput priority Context
Short chat (Q&A) Low Concurrency ≤ 8k
Long RAG (multi-document) Medium Balanced 8-32k
Long context (tenders / contracts) High Latency 128k+
Training / fine-tune Very high Throughput N/A

Do not mix training and inference on the same GPUs without K8s + Slurm hybrid orchestration. See Case 13 for a 128-GPU real setup.

Step 4 · Pick Model + Embedding + Reranker Triple

All three together. Model in isolation is meaningless.

Task Model Embedding Reranker
Doctor guideline lookup AW36-72B bge-large BGE-reranker
Air-gapped factory RAG AW36-14B bge-large (single-tenant, skip)
Cross-border SaaS (cost-optimized) AW36-Max + Claude 3.5 m3e BGE-reranker

Step 5 · Size Storage IO

Storage IO is often the bottleneck, not GPU.

Step 6 · Set Cost Cap Upfront

If nothing is capped, prod cost balloons 3-10× in 6 months.

See Case 03 for a group-wide multi-tenant gateway with all three enforced.

Only Then, Decide Hardware

Signal Hardware
72B + high concurrency 4-8×A800 (vLLM)
14B-32B + single-tenant 1×4090 / RTX 6000 Ada
Training + inference share K8s + Slurm hybrid on A800 cluster
Air-gapped workshop Single 4090 edge
Cost-optimized cross-border Public API + selective on-prem gateway

Common Failure Modes


Next: Download portfolio PDF · 30-min sizing alignment