plawanrath/mistral-7b-instruct-v0.3-q8-mlx-cba

mistral-7b-instruct-v0.3-q8 (MLX, CBA artifact)

MLX-format 8-bit (Q8) variant of mistralai/Mistral-7B-Instruct-v0.3.

This is one of the 15 model artifacts from the paper:

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels Plawan Kumar Rath, Rahul Maliakkal. IEEE Cloud Summit 2026. Code: https://github.com/plawanrath/compression-bias-amplification arXiv: https://arxiv.org/abs/2605.15208

Quantization

Weight-only post-training quantization via mlx_lm.convert:

• bits: 8
• group_size: 64
• mode: affine

How this artifact was produced

python -m mlx_lm.convert \
    --hf-path mistralai/Mistral-7B-Instruct-v0.3 \
    --mlx-path ./mistral-7b-instruct-v0.3-q8 \
    --quantize \
    --q-bits 8 \
    --q-group-size 64

This is the exact artifact used to produce the inference results in §4.3 of the paper (911,100 records over BBQ ambiguous, 5 seeds × 12,148 items × 15 configs).

Usage (MLX)

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("plawanrath/mistral-7b-instruct-v0.3-q8-mlx-cba")
prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Hello!"}],
    add_generation_prompt=True,
    tokenize=False,
)
print(generate(model, tokenizer, prompt=prompt, max_tokens=128))

Or via CLI:

mlx_lm.generate --model plawanrath/mistral-7b-instruct-v0.3-q8-mlx-cba --prompt "Hello!"

Paper findings relevant to this variant

The paper documents a dose-response relationship between quantization aggressiveness and emergent stereotypical behavior on BBQ ambiguous questions:

Variant	% of BF16-unbiased items that became biased
Q8	0.1–0.9%
Q6	0.3–1.3%
Q4	2.2–5.6%
Q3	6.0–21.1%

These changes are largely invisible to perplexity (<0.5% shift at Q8, <3% at Q4 across all three families). Treat any deployment of compressed instruction-tuned models on fairness-sensitive tasks accordingly.

Model details

• Base model: mistralai/Mistral-7B-Instruct-v0.3
• Family: Mistral
• Parameters: 7.2B
• Precision: 8-bit (Q8)
• Format: MLX (Apple Silicon)
• Conversion framework: mlx-lm

License

Inherited from the base model (apache-2.0). See the upstream model page for the full license text.

Citation

@inproceedings{rath2026quantization,
  title     = { Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels },
  author    = {Rath, Plawan Kumar and Maliakkal, Rahul},
  booktitle = { IEEE Cloud Summit 2026 },
  year      = {2026},
  eprint    = {2605.15208},
  archivePrefix = {arXiv},
  url       = {https://arxiv.org/abs/2605.15208}
}

Disclaimer

Plawan Kumar Rath (@plawanrath). This work was conducted in the author's personal capacity. The views expressed here are those of the author and do not necessarily reflect the views of Meta.