# iOS Swift on-device and cloud LLM

iOS Swift work covers CoreML or MLX paths, Speech framework combinations, Keychain-backed keys, and App Store-safe logging without leaking prompts in OSLog. We benchmark on-device tokenizers on Polish legal vocabulary. €2,400 PoC; €3,900 prototype; €3,100 Eval CI with XCTest hooks; €5,600 hardening; €8,500 MVP; audit from €8,000. Privacy-first designs stay explicit, no hidden cloud exfiltration after scope sign-off. Written scope arrives within 48 hours with numeric pass marks on accuracy, groundedness, p95 latency, and cost per thousand runs; deliverables include Dockerized repos, handoff notes, and Promptfoo or DeepEval fixtures your team can extend.

**Sprints from €2,400 PoC · €3,100 eval CI · €3,900 prototype · €5,600 hardening · €8,500 MVP · audit from €8,000** · Topic: `engineering-ios-swift` · [Open proof](/#open-proof) · [Sample scorecard](/sample)

HTML: [/engineering/ios-swift](/engineering/ios-swift) · Markdown: [/engineering/ios-swift.md](/engineering/ios-swift.md)


_On-device privacy-first LLM paths_

## Why teams trust this stack with Arviser

- Stack-specific gates for iOS Swift on-device and cloud LLM, not generic AI slideware.
- Senior engineers (10+ yrs) with daily eval tooling; founder architecture review (30+ yrs IT).
- Proof links include Open proof and sample scorecards, commercial sprints stay fixed-scope.

## Dual path

### For CTO / Staff Eng

Senior engineers (10+ yrs) build the vertical slice, wire retrieval and tools, and leave a repo your team can extend, with modular prompts, typed tool schemas, and CI eval fixtures.

### For VP Product / CFO

Fixed-hour packages (€2,400–€8,500) de-risk AI spend: kill fees on Risk-Shared PoC when narrow hypotheses fail, 100% PoC credit toward MVP on Go, and no surprise T&M overruns inside written scope.

Route: 24h PoC (€2,400) if unknown feasibility, else 40h Prototype (€3,900); add 32h Eval CI (€3,100) before scale; harden at €5,600 or ship MVP at €8,500.

## Stack-specific failure modes we gate in eval CI

- CoreML model warm-up on background thread blocks UI when combined with Speech framework.
- Keychain-stored API keys logged by OSLog when debug logging left on in TestFlight.
- On-device tokenizer truncates Polish legal terms, increasing hallucination rate.

### Sample eval fragment (ios-swift)

```
let gate = EvalGate(minGroundedness: 0.87, maxP95Ms: 1200)
```

## Which sprint fits?

| Situation | Recommendation | Sprint |
| --- | --- | --- |
| Hard unknown on this stack | 24h Technical PoC | €2,400 · 3–5 days |
| Working demo, no CI evals | 32h Eval CI harness | €3,100 · 1 week |
| Pilot traffic soon | 60h Hardening or 80h MVP | €5,600–€8,500 |

## FAQ

### Do you build iOS Swift on-device and cloud LLM under fixed scope?

Yes. We deliver written scope in 48h and fixed-hour packages; overruns inside agreed spec are on us.

### Can we start with eval CI only?

Yes, 32h Eval CI from €3,100 when a prototype exists but gates do not.

Reviewed by Vadim Nareyko, 30+ yrs IT · Last updated 2026-11-06

## Related

[Mobile hub](/engineering/mobile) · [Cross-platform](/engineering/cross-platform)

