Blog

What AI inference is, how it works, how it differs from training, what it costs, and how to make it faster and cheaper. A plain guide.

Sparset’s open-weight Qwen3.5-4B fine-tune for document synthesis scored 95.22 vs 91.16 on an internal 500-case test. See the recipe, results and limits.

We explore how fine-tuning changes generation in two small reasoning models. Nanolite 0.6B delivered answers 3.28× faster in a workplace pilot, while Nanolite V2 used about 92% fewer tokens on mutually completed GSM8K and BBH questions. The experiments reveal both the potential of shorter reasoning and the quality tradeoffs behind the speedups.

An experimental engine that reads a pretrained LLM’s scores for known answers instead of generating JSON. 26x faster by median latency, limits stated.

Why running your own AI model is harder than it should be, what Sparset does about it, and the measured results from a customer in production.

Ora Frontier is now Sparset. What changed, what stayed the same, and what the new name means for teams running AI on their own infrastructure.