phi-3.5-mini-instruct-bf16 (MLX, CBA artifact)
MLX-format BF16 (uncompressed baseline) variant of microsoft/Phi-3.5-mini-instruct.
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
This is the BF16 baseline used as the uncompressed reference in the paper. Weights have been re-serialized via mlx_lm.convert (no quantization) so this directory is loadable directly by MLX without an extra conversion step.
How this artifact was produced
python -m mlx_lm.convert \
--hf-path microsoft/Phi-3.5-mini-instruct \
--mlx-path ./phi-3.5-mini-instruct-bf16 \
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/phi-3.5-mini-instruct-bf16-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/phi-3.5-mini-instruct-bf16-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:
microsoft/Phi-3.5-mini-instruct - Family: Phi-3
- Parameters: 3.8B
- Precision: BF16 (uncompressed baseline)
- Format: MLX (Apple Silicon)
- Conversion framework:
mlx-lm
License
Inherited from the base model (mit). 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.