Meta released Llama 3.2 with models as small as 1B and 3B, specifically designed for on-device execution. A look at what they can actually do and how they compare to alternatives.
Read moreLlama 3.2 at the edge: Meta bets on small
Tag: edge
Cloudflare Workers in 2025: from edge to enterprise
Cloudflare Workers turns eight and has become a full application platform. A review of what it offers today, what limitations persist, and where it makes sense to bet.
Read moreNPU in the PC: faster, cheaper local AI
Copilot+ processors from Qualcomm, Intel, and AMD have normalized NPUs in consumer PCs. What really changes for running local models, and when it’s worth it.
Read moreCloudflare Workers in 2024: KV, D1, and the New Edge Stack
Workers + KV + D1 + R2 + Durable Objects form a complete edge stack. What’s missing, what works, and when it competes with AWS.
Read moreWASI 0.2 GA: Truly Composable WebAssembly
WASI 0.2 brought the Component Model to GA. How it changes server-side WebAssembly portability and what cases are viable today.
Read moreDeno Deploy: TypeScript at the Edge Without a Server
Deno Deploy is the edge-serverless offering from Deno’s creators. What it brings vs Workers and Lambda, when it fits, and where it falls short.
Read moreFastly Compute: High-Performance Edge with WebAssembly
Fastly Compute runs WebAssembly code across hundreds of PoPs. How it compares with Workers, where it performs better, and when migrating makes sense.
Read more