--- language: - en - zh - fr - es - pt - de - it - ru - ja - ko - ar - vi - th - nl - pl license: apache-2.0 library_name: mlx base_model: Qwen/Qwen3.6-27B tags: - 4-bit - 4bit - apple-silicon - best-quality - chat - conversational - edge-ai - flagship - function-calling - humaneval - instruct - local-llm - m1 - m2 - m3 - m4 - mac - mac-mini - mac-studio - macbook-air - macbook-pro - macos - metal - mlx - mlx-lm - no-cloud - offline - on-device - outlier - outlier-app - private - private-ai - quantized - qwen - qwen3.6 - qwen3_5 - reasoning - safetensors - text-generation - thinking - tool-use pipeline_tag: text-generation model-index: - name: Outlier-Ai/Outlier-Core-27B-MLX-4bit results: - task: type: text-generation name: Text Generation dataset: name: MMLU (200-question sample, build 1.11.804, 2026-08-24) type: cais/mmlu metrics: - type: acc name: accuracy value: 0.8950 verified: false - task: type: text-generation name: Text Generation dataset: name: HumanEval (all 164, build 1.11.804, 2026-08-24) type: openai_humaneval metrics: - type: pass@1 name: pass@1 value: 0.9512 verified: false --- > **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 for Mac: free Nano and Lite; Pro is **$49 once**, on up to 3 Macs · `brew install --cask outlier-host/tap/outlier` # Outlier Core 27B (MLX 4-bit) **What this is:** Qwen3.6-27B, text-only, converted to MLX 4-bit. Nothing else is changed: no fine-tune, no merge. It is the Core tier of the Outlier app for Mac, which downloads exactly these files. - Download size: 15.13 GB · minimum unified memory: 24 GB · Apple silicon - Licence: Apache 2.0, the base model's licence. The Outlier team converted the weights; the model is the base model's authors' work. - In the app: part of Pro ($49 once) ## Measured results These are the figures on [outlier.host](https://outlier.host/data/outlier-tier-benchmarks-2026-08/?utm_source=hf&utm_medium=modelcard), with how each was run. Small samples: at n=200 an MMLU figure can be off by up to 7 points either way. | Test | Result | How | |---|---|---| | MMLU | 89.5% (179/200) | a 200-question sample, build 1.11.804, 2026-08-24 | | HumanEval | 95.1% (156/164) | all 164 problems, official tests, build 1.11.804, 2026-08-24 | | SWE-bench Verified (agentic) | 46.0% (23/50), blind, official Docker harness, build 1.11.757, 2026-08-09 | a random 50-task sample (seed 42), no test patch or file hint | | Decode speed, M1 Ultra | 20.7 tok/s (measured 2026-04-29) | | The app you download is a later build than the one measured; these figures have not been re-run on it. ## Use it The easiest way is the [Outlier app](https://outlier.host/?utm_source=hf&utm_medium=modelcard): pick **Outlier Core** in the model picker and it downloads these files. To load the weights yourself: ```bash pip install mlx-lm python -m mlx_lm.generate --model Outlier-Ai/Outlier-Core-27B-MLX-4bit --prompt "Hello" --max-tokens 256 ``` ## The other Outlier tiers - [Outlier Nano 4B](https://huggingface.co/Outlier-Ai/Outlier-Nano-4B-MLX-4bit) (free) - [Outlier Lite 9B](https://huggingface.co/Outlier-Ai/Outlier-Lite-9B-MLX-4bit) (free) - [Outlier Quick 26B (MoE)](https://huggingface.co/Outlier-Ai/Outlier-Quick-26B-MLX-4bit) (Pro) - [Outlier Plus 397B (Qwen3.5-397B-A17B, a public community conversion)](https://huggingface.co/mlx-community/Qwen3.5-397B-A17B-4bit) (Pro) - [Outlier Vision 3.8 27B (Qwen3.8-27B, a public community conversion)](https://huggingface.co/mlx-community/Qwen3.8-27B-4bit) (Pro) Earlier experiments in this organisation (Outlier-10B, -40B, -70B, -150B and others) are research checkpoints. The app does not ship them.