Apple Intelligence Server Models by Apple Machine Learning Research
Last refreshed 2026-04-15. Next refresh: weekly.
Details
About
Apple's Intelligence system harnesses the power of a family of large language models (LLMs) known for their robust architecture and adaptability. Central to this suite is the AFM-server, a massive cloud-based model crafted from the ground up. It significantly surpasses the compact, 3-billion parameter AFM-on-device model in size. Both models share a Transformer decoder-only structure and have been pre-trained on an extensive dataset of 6.3 trillion tokens. While the AFM-server is designed without pruning from a larger model, Apple enhances functionality using pluggable LoRA adapters, which allow the models to be dynamically adapted for specific tasks. This results in efficient and tailored performance without comprehensive retraining. In parallel, the OpenELM models, part of Apple’s innovation, utilize strategic layer-wise scaling for optimal parameter distribution, are available in various parameter sizes, and stand out as open-source, unlike the proprietary AFM models 136.
Decision facts
- Best fit
- coding
- Capability starting point
- Apple Server
- Lowest tracked input
- Not tracked
- Closest related family
- OpenELM
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Apple Server | Use when provider availability and model metadata match the workload. | 2024-06 | — | Current |
Release Timeline
1 release groupSpecifications(1 models)
| Model | Released |
|---|---|
| Apple Server | 2024-06 |
