Mistral Launches Shieldstral: A 3B Parameter Open-Source Safety Classifier
dl_weekly · x · 2026-08-10
Mistral has introduced Shieldstral, a 3B parameter multimodal safety classifier released under the Apache 2.0 license. The model is designed to take plain-language policies directly at inference time.
Performance & Deployment:
- Delivers robust performance, matching guard models up to 7x its size.
- Highly efficient to deploy, running entirely on a single 16GB GPU, making it accessible for developers to integrate into AI applications as a guardrail.
Related event: Mistral Releases Shieldstral 3B Open-Source Moderation Model(2 posts)→
More from Models
- willcb: Opus 5.5 doesn't smell bigger, it smells like they fixed the data — willcb · 2026-10-16
- Unverified claim: Apple and Meta's 816B-parameter Muse Spark Open runs on two Mac Studios — TansuYegen · 2026-10-16
- Gemini 4 model card: model eliminated months of trial-and-error on bioweapons research — Puzzleheaded-King584 · 2026-10-16
- Every AI picks 7: Anthropic engineer's rule for escaping model taste convergence — rubenhassid · 2026-10-16
- Brain teaser: strip all attention, MLP and embedding matrices from a Llama 3 — how many trainable params remain? — Sauers_ · 2026-10-16
- Lean v4.35.0 ships verified kernels — one written and proven consistent by Claude — geoffreyirving · 2026-10-16