Rolling out selective 4-bit weight-only quantization for supported models, targeting non-sensitive layers...
UpdateUnverifiedAdded Sep 24, 2026
Rolling out selective 4-bit weight-only quantization for supported models, targeting non-sensitive layers while preserving full precision for sensitive layers, in line with industry standards. Learn more in Supported Models.
More Cerebras Inference releases
Every Cerebras Inference releaseAlso shipped on Mar 27, 2026
Cerebras in March 2026| Date | Company | Release | Product | Type |
|---|---|---|---|---|
| Mar 27 | Deploy from Codex with the Netlify Pluginunverified | Netlify | Preview | |
| Mar 27 | Qdrant 1.17.1unverified | Qdrant | Update | |
| Mar 27 | Cache prewarm, Stripe Projects integration, Neon Auth webhooks with Resend, and more release - Mar 27, 2026unverified | Neon | Update | |
| Mar 27 | What's new in Sigmaunverified | Sigma | Update | |
| Mar 27 | Workers - New RFC 9440 mTLS certificate fields in Workersunverified | Cloudflare developer platform | Update | |
| Mar 27 | One-click CDN, Railway x Stripe Projects, HA Postgresunverified | Railway | Update |
Sources: each vendor's own release notes, changelogs and GitHub releases, read daily to monthly by how often it posts. Logos via logo.dev; trademarks belong to their owners.