vLLM v0.33.0rc3: CUDA 13.0, new MoE models and speculative decoding on AMD
Tools & releasesRelated articles
Intel and AMD collaborate on PyTorch/oneDNN: what it means for local AI on CPUs
AMD is merging ZenDNN into oneDNN and Intel is folding in its ACE extensions: one open-source x86 acceleration stack in PyTorch, already the default. What it changes if you run models locally on CPUs.
Qwen3.8-27B vs Gemma 4 26B A4B: the new frontier at 24GB
A 27.8B dense or a MoE with 3.8B active, a 262K context against 256K and almost the same weight at Q4_K_M: two opposite ways of putting big-model quality on a 24GB consumer card. Which is faster, which goes deeper, and when to pick one over the other.
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.
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.

