AI article
A 2.6B model on an iPhone that always answers in valid JSON
Community description: Running LFM2-2.6B with llama.cpp fully offline on an iPhone 15: numbers, grammar-constrained JSON, and five problems we had to solve.
Dev.to | Oct 31, 2026 | theyplaygames
Automated excerpt
Runtime: llama.cpp b11887 as an xcframework, Metal for all layers, n_ctx = 4096 Asking a 2B model to "answer in JSON" works most of the time. We stopped asking the model for numbers we can read with rules: the amount next to Total / Summe / ご請求金額 / 合計, dates, IBANs. The model writes the summary and the steps, the rules provide the facts, and the facts override the model.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.