01 - SLM in 2026: Overview of Models and Benchmarks
SLM nel 2026: Panoramica dei Small Language Models e Benchmark Nel 2023 "modello AI" significava quasi sempre GPT-4 o Claude.
Small Language Models
Series “Small Language Models”: it starts with “03 - SLM Fine-tuning with LoRA and QLoRA: Practical Guide”. Fine-tuning SLM with LoRA and QLoRA: Complete Practical Guide In 2021, fine-tuning a 7B parameter model required 8 GPUs of 80GB each and weeks of compute. Today, QLoRA makes it possible on consumer GPUs. Learn LoRA…
This series collects 3 articles (approximately 45 minutes of total reading time), designed for a level Intermediate. The main topics covered are Phi-4-mini, SLM, Gemma 3, SmolLM2.
3Articles45 minTotal reading timeIntermediateLevel
Phi-4-miniSLMGemma 3SmolLM2Qwen 3Gemma 3n
Series Articles
- 1
- 2
02 - Phi-4-mini and Gemma 3: Microsoft vs Google for the Edge
Phi-4-mini vs Gemma 3n: Microsoft contro Google per l'Edge AI Due giganti tecnologici, due filosofie diverse, entrambi con l'obiettivo di creare il...
- 3
03 - SLM Fine-tuning with LoRA and QLoRA: Practical Guide
Fine-tuning SLM with LoRA and QLoRA: Complete Practical Guide In 2021, fine-tuning a 7B parameter model required 8 GPUs of 80GB each and weeks of compute. Today, QLoRA makes it possible on consumer GPUs. Learn LoRA, QLoRA, PEFT, and TRL with hands-on examples.