SWE-bench — The standard benchmark for AI coding agents: real GitHub issues from real repositories, scored by whether the agent's patch passes the project's own tests.
quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
Why it matters
An open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → 33B-A3B coding model now runs locally at 256K context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → with quantizationShrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.Full definition → FP8/INT4/NVFP4 checkpoints and speculator models that roughly double throughput, under a permissive OpenMDW license.
