Models
Open-Weight vs Closed Models: The Decision Isn't Capability
Benchmark parity is real for routine work. The choice turns on residency, version pinning, and where your cost curves cross.
#open weights
6 articles6 articles on Model Drop tagged "open weights."
6 articles
-
-
ModelsEvery Model Family That Matters in Late 2026
Six families, four tiers each, and a flagship price everyone agrees on. The real differences aren't on any benchmark chart.
-
PlatformsInference Providers Compared: Price Is the Wrong First Question
Rate limits and p99 latency decide more deployments than per-token pricing. Plus why identical weights serve differently.
-
LaunchesDeepSeek V4 and the Open-Weight Price Ceiling
Open weights near the frontier on published scores. The useful question is what that equivalence is measuring — and what it buys you.
-
ModelsSmall Models That Run on One GPU, and What They Cost You
A quantized 27B model fits in 24 GB and handles most routine work. Throughput, not capability, is what actually limits it.
-
PlatformsSelf-Hosting vs API Inference: Utilization Decides It
Free weights are not free inference. The cost case lives on a utilization curve, and residency is a better reason anyway.