Tag: apple silicon

3 entries tagged "apple silicon" — 2 posts, 1 link.

Posts

Mar 20, 2026 — 8 min — Platform & AI

Fine-Tuning GPT-OSS 20B on a 64GB MacBook Pro

A practical MLX-first recipe for experimenting with openai/gpt-oss-20b on a 64GB Apple Silicon Mac without confusing local LoRA work for CUDA-scale training.

gpt-oss mlx

Mar 16, 2026 — 7 min — Platform & AI

Fine-Tuning LLMs on a MacBook Pro With MPS and MLX

Why Apple Silicon is useful for local LLM prototyping and LoRA experiments, but still has sharp boundaries compared with CUDA-scale NeMo or Hugging Face training.

apple silicon mlx

Links

Articlegimletlabs.aiApr 14, 2026Permalink

Speeding up PyTorch inference on Apple devices with AI-generated Metal kernels

Taras Sereda, Gimlet Blog

This is a strong local-inference link because it shows the gap between framework support and hardware-specific performance work. Apple Silicon can be serious, but the path often goes through kernels, not just model.to("mps").

The AI-generated-kernel angle is interesting, but the bigger point is operational: when the backend is the bottleneck, model.to("mps") is only the start.

All tags