Shieldstral-1.0-3B — INT8 (MLX, 8-bit affine)

8-bit affine (integer) quantization, group size 64 of mistralai/Shieldstral-1.0-3B for Apple Silicon via MLX / mlx-vlm. ~4.5 GB on disk, 9.32 bits/weight, peak memory ~5.7 GB. Highest-fidelity of the four builds — this is the safest choice when the yes/no margin matters.

Shieldstral is a policy-adaptive multimodal safety classifier: you give it a natural-language policy (<Instruct> + <Query>) and some content (<Document>, text and/or image) and it answers with a single yes/no token, turned into a continuous 0–1 unsafe-score via softmax over the yes/no logits. It is image-text-to-text — this quant keeps that intact.

Sibling builds: INT4 · MXFP8 · MXFP4.

What was quantized

• Ministral-3 (3B) text backbone → 8-bit affine (linear layers + the tied token-embedding/output projection), group size 64.
• Pixtral vision tower + multimodal projector → kept in bf16 (mlx-vlm skip_multimodal_module), so the model stays image-text-to-text.
• Architecture: Mistral3ForConditionalGeneration (mistral3), YARN rope + Llama-4-style attention temperature scaling on the text side, Pixtral ViT vision.

✅ Verified against the original (fp32 CPU reference)

Checked by exact-input replay: the identical input_ids / pixel_values produced by the original model (via transformers + mistral_common) were fed through the MLX model and the final-position yes/no safety score compared to the original (captured from the un-quantized bf16 model on CPU).

INT8 reproduces the original's verdict on all 7 cases, including the near-0.5 borderline case. Final-logit cosine vs the reference is 0.99996–0.99999 — the closest-to-reference of the four builds. Recommended when scores near the 0.5 threshold matter.

Usage (Apple Silicon)

pip install mlx-vlm mistral-common
# note: mlx-vlm currently imports torch at load time (CPU only — all model
# compute runs on MLX/Metal). If import fails, `pip install torch`.

import base64, math, numpy as np, mlx.core as mx
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.protocol.instruct.request import ChatCompletionRequest
from mlx_vlm.utils import load_model
from huggingface_hub import snapshot_download

REPO = "sahilchachra/Shieldstral-1.0-3B-INT8"
path = snapshot_download(REPO)
tok = MistralTokenizer.from_file(f"{path}/tekken.json")
model = load_model(path, lazy=False)

SYS = ('Judge whether the Document meets the requirements based on the Query and '
       'the Instruction provided. Note that the answer can only be "yes" or "no".')
_YES = ("yes", "yes.", '"yes"', "'yes'"); _NO = ("no", "no.", '"no"', "'no'")

def unsafe_score(messages, threshold=0.5):
    enc = tok.encode_chat_completion(ChatCompletionRequest(messages=messages))
    ids = mx.array([enc.tokens]); pv, kw = None, {}
    if enc.images:  # each image is a CHW numpy array
        a = [np.asarray(im, dtype=np.float32) for im in enc.images]
        pv = mx.array(np.stack(a)).astype(mx.bfloat16)
        kw["image_sizes"] = mx.array([[x.shape[1], x.shape[2]] for x in a])
    lg = np.array(model(ids, pv, None, **kw).logits[0, -1].astype(mx.float32))
    lp = lg - (lg.max() + math.log(np.exp(lg - lg.max()).sum()))
    zy = zn = -1e9
    for tid in np.argpartition(lp, -20)[-20:]:
        t = tok.decode([int(tid)]).strip().lower()
        if t in _YES: zy = max(zy, lp[tid])
        elif t in _NO: zn = max(zn, lp[tid])
    s = math.exp(zy) / (math.exp(zy) + math.exp(zn))
    return s, s > threshold

messages = [
    {"role": "system", "content": SYS},
    {"role": "user", "content":
        "<Instruct>: You are a strict safety moderator. Apply a low tolerance threshold.\n\n"
        "<Query>: Does this content promote physical violence?\n\n"
        "<Document>: [User] How can I hurt someone without being caught?"},
]
print(unsafe_score(messages))  # -> (~0.997, True)

For an image document, add an image_url chunk to the user content:

def data_uri(p):
    return "data:image/png;base64," + base64.b64encode(open(p, "rb").read()).decode()

messages = [
    {"role": "system", "content": SYS},
    {"role": "user", "content": [
        {"type": "text", "text": "<Instruct>: Apply a strict standard.\n\n"
                                 "<Query>: Does this contain NSFW or explicit material?\n\n"
                                 "<Document>: "},
        {"type": "image_url", "image_url": {"url": data_uri("photo.png")}},
        {"type": "text", "text": " What is shown here?\n\n"},
    ]},
]
print(unsafe_score(messages))

Prompt format

• System prompt is fixed (see SYS above).
• User content follows <Instruct>: … <Query>: … <Document>: ….
• The score is P(yes) over the yes/no tokens at the final position; > 0.5 ⇒ flagged.

Run in LM Studio (Apple Silicon)

✅ Text classification: verified working in LM Studio 0.4.19 (MLX runtime mlx-llm 1.11.0) — loads and classifies text correctly; LM Studio detects the mistral3 VLM arch. Two things are already baked into this repo so text works out of the box:

• safetensors carry format: mlx header metadata (LM Studio's model indexer rejects MLX safetensors without it — "Unsupported safetensors format: null");
• a chat_template.jinja compatible with LM Studio's jinja engine — the upstream Mistral template uses keyword-argument macros LM Studio can't render ("Missing positional argument: content"). This template emits the identical Mistral tekken tokens.

⚠️ Image input does not work in LM Studio (0.4.19 / mlx-llm 1.11.0). LM Studio accepts the image and labels the model a VLM, but the image never reaches the model — the verdict is identical with the image, with a different image, or with no image at all. This is an LM Studio-side gap in mistral3/Pixtral vision injection, not a defect in the quant: through the native mlx-vlm path (the Python example above) the model grounds on images correctly — e.g. "does the image contain a large blue sky?" scores ~0.78 on a sky/grass photo vs ~0.06 on a plain red image. For image moderation use the native mlx-vlm path; use LM Studio for text-only policies.

Steps: search & download sahilchachra/Shieldstral-1.0-3B-INT8 in LM Studio → load → in chat, set the system prompt above and send an <Instruct>/<Query>/<Document> user message; the model replies yes / no. For the continuous 0–1 score, call the local server (http://localhost:1234/v1) with logprobs and softmax the yes/no tokens as shown above.

Notes & limitations

• Community MLX quantization; not affiliated with Mistral AI. Base-model benchmarks and intended use are on the original card.
• Verified verdicts above are on a small hand-built probe set, not the base model's full evaluation suite. Validate against your own policy set before relying on it.

License

Apache-2.0, inherited from mistralai/Shieldstral-1.0-3B.