Instructions to use Outlier-Ai/Outlier-Vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Outlier-Ai/Outlier-Vision with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download Outlier-Ai/Outlier-Vision --local-dir Outlier-Vision
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Research checkpoint. Not shipped in the Outlier app. Numbers below are from internal experiments, not our release tests. Shipped models: Nano 4B ยท Lite 9B ยท Quick 26B ยท Core 27B.
Superseded. This repo is a research artifact from an earlier Outlier lineage and is no longer the recommended download. The current shipping tier is at outlier.host. Outlier for Mac: free Nano and Lite; Pro is $49 once, on up to 3 Macs ยท
brew install --cask outlier-host/tap/outlier
Outlier-Vision
This repo predates the v1.8 Outlier lineup. It is preserved here for reproducibility and historical reference, not as a production recommendation.
What replaced it
Current shipping tiers (see Outlier app v1.8+):
- Outlier Nano 4B โ current entry tier
- Outlier Core 27B โ current default tier
- Outlier Vision 35B-A3B โ current multimodal tier
- DeepSeek-R1-Distill-Qwen-7B โ popular reasoning model
- Qwen3-Coder-30B-A3B โ popular coding model
For the latest verified benchmarks and downloads, visit outlier.host.
Original notes
This was a research / preview artifact. It may contain experimental adapters, overlays, or quantization variants that did not graduate into the shipping product. Treat any technical claims in earlier revisions of this card as provisional.
License
See YAML frontmatter above. Original license terms preserved.
- Downloads last month
- 59
4-bit