majentik/Shieldstral-1.0-3B-MLX-MXFP4

Shieldstral-1.0-3B-MLX-MXFP4

MLX MXFP4 (mxfp4, group size 32) quantized variant of mistralai/Shieldstral-1.0-3B — Mistral's content-safety / moderation model — for Apple silicon via mlx-lm.

Provenance

• —Source: mistralai/Shieldstral-1.0-3B @ revision 003ec7e2b0bab5f0e6307edbaf186fa5822b76f5 (Apache-2.0).
• —Quantized with mlx_lm.convert (mlx-lm 0.31.3): mxfp4, 4-bit, group size 32.
• —Text-only pack: the upstream checkpoint is a mistral3 multimodal wrapper; mlx-lm's mistral3 loader drops the vision tower by design, so this pack ships only the Ministral-3B text model. Use the upstream repo if you need image moderation.

Caveat

This is a quantized safety classifier. Quantization can shift borderline classification decisions; validate against your own moderation benchmark before using a quantized tier in production guardrails. Prefer the 8bit tier when in doubt.

Smoke gate

Before upload this pack passed a deterministic coherence gate: greedy 64-token moderation-style chat generation loaded through mlx_lm.load, judged for emptiness, repetition loops, multi-script gibberish, and special-token debris. Verdict: ok.

Usage

pip install mlx-lm
mlx_lm.generate --model majentik/Shieldstral-1.0-3B-MLX-MXFP4 \
  --prompt "Classify as SAFE or UNSAFE: 'how do I sharpen a kitchen knife?'"

Evaluation

Available tiers