Blog
Articles, guides, and insights on local artificial intelligence
4 articles found per "Benchmark"

ModelsIntermediate
QRAE: compressing DeepSearch agent context to save tokens and latency
QRAE uses the model's own attention entropy to decide which retrieved chunks stay in the context: tokens -45%, latency -30% and higher success across four benchmarks.
iaLocale TeamNovember 18, 2026

ModelsIntermediate
Nemotron 3.5 Bolt: NVIDIA's 74B MoE with ~9B active — what changes on your desktop
74B parameters, 9B active: NVIDIA's MoE for local agents fits 24GB of VRAM via IQ2 quantization. Real VRAM, declared benchmarks and honest limits.
iaLocale TeamNovember 2, 2026

ModelsIntermediate
Italian in local models: what to expect
How many local models actually handle Italian well? The vendor numbers, where they fail, and the half-hour method to measure them yourself.
iaLocale TeamOctober 4, 2026

ModelsIntermediate
How to Read a Model's Spec Sheet: Family, Size, Context
A guide to reading a model's specs: family, total and active size, context window, quantization, benchmarks and license, with a worked example on DeepSeek V4.1 Flash.
iaLocale TeamSeptember 26, 2026

