llama.cpp b12122: NVFP4 gate/up matmuls and GLU fused in MMQ on CUDA, one kernel for the quantized MLP block
Tools & releasesRelated articles
NVIDIA, AMD and Intel for local AI: which platform to choose
CUDA, ROCm or Vulkan? We compare the three local-AI platforms based on what is actually available: official software stacks, cards by VRAM tier (12, 16 and 24GB) and real speeds. Where the obvious choice remains, where AMD wins on value, and when it makes sense to leave NVIDIA.
Qwen: the open model with the best multilingual support
Qwen is the open family with the best support for Italian and French: generations, sizes, MoE, when to use it, and a quick comparison with Llama.
Llama 3 and Llama 4: Meta's open family — which model runs on your hardware
From the 3.1 8B to the 4 Scout MoE with a 10M context: the Llama family in a table, what runs on 16, 48 and 128 GB of RAM, the Community license translated for the Italian business and the choice by budget.
Get the next local-AI briefing
Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.
After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

