Outlier-Ai/Outlier-Core-27B-MLX-4bit

Part of the [Outlier](https://outlier.host/?utm_source=hf&utm_medium=modelcard&utm_campaign=outlier_core_27b_mlx_4bit) shipping lineup. Outlier is a free macOS app that runs this model locally, with one click. Apple Silicon only.

Outlier Core 27B (MLX 4-bit)

The default shipping tier for 24 GB+ Macs. 27B dense, text-only, MLX 4-bit. Ships with a Holtzman calibration bias applied at inference time (pure post-processing, no weight modification).

Try it in Outlier

The simplest way to use this model is through the Outlier app — open the tier picker, select Outlier Core, click download, and chat. No setup, no Python, no MLX install, no token quotas.

➡ [Download Outlier — outlier.host](https://outlier.host/?utm_source=hf&utm_medium=modelcard&utm_campaign=outlier_core_27b_mlx_4bit)

A screenshot of the tier picker is at outlier.host/screenshots/tier-picker.png.

Load this directly (power users)

If you want the raw MLX-4bit weights without the app:

pip install mlx-lm
python -m mlx_lm.generate \
  --model Outlier-Ai/Outlier-Core-27B-MLX-4bit \
  --prompt "Write a quicksort in Python." \
  --max-tokens 512

from mlx_lm import load, generate
model, tokenizer = load("Outlier-Ai/Outlier-Core-27B-MLX-4bit")
print(generate(model, tokenizer, prompt="Hello", max_tokens=256))

Verified benchmarks

For σ-qualified MMLU, HumanEval, and Mac inference-speed numbers — with full provenance (source file, command, n, stderr, date) — see [outlier.host/benchmarks](https://outlier.host/benchmarks?utm_source=hf&utm_medium=modelcard&utm_campaign=outlier_core_27b_mlx_4bit).

Other Outlier shipping tiers

• —Outlier Nano 4B (entry tier, ~3 GB)
• —Outlier Lite 9B (balanced, ~6 GB)
• —Outlier Quick 26B-A4B MoE (~16 GB)
• —Outlier Code 27B (code-tuned, ~16 GB)
• —Outlier Vision 35B-A3B (multimodal, ~20 GB)

License

Apache 2.0 (inherits from upstream base model). Conversion artifact only — the underlying weights are governed by the base model's license.