OpenELM Models by Apple Machine Learning Research
Apple Machine Learning ResearchProprietary
4 models2024
Last refreshed 2026-05-19. Next refresh: weekly.
Details
ResearcherApple Machine Learning Research
LicenseProprietary
Commercial useCommercial use: conditional
Models4
Released2024
About
Open Efficent Language Model
Decision facts
- Best fit
- General model comparison
- Capability starting point
- OpenELM 270M
- Lowest tracked input
- Not tracked
- Closest related family
- Apple Intelligence Server
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
4 in view
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| OpenELM 270M | Use when the workload needs 270M parameters. | 2024-04 | 270M parameters | Current |
| OpenELM 450M | Use when the workload needs 450M parameters. | 2024-04 | 450M parameters | Current |
| OpenELM 1.1B | Use when the workload needs 1.1B parameters. | 2024-04 | 1.1B parameters | Current |
| OpenELM 3B | Use when the workload needs 3B parameters. | 2024-04 | 3B parameters | Current |
Release Timeline
1 release group2024-04
4 current
OpenELM 1.1B
Current1.1B parameters
OpenELM 270M
Current270M parameters
OpenELM 3B
Current3B parameters
OpenELM 450M
Current450M parameters
Specifications(4 models)
| Model | Released | Parameters |
|---|---|---|
| OpenELM 270M | 2024-04 | 270M |
| OpenELM 450M | 2024-04 | 450M |
| OpenELM 1.1B | 2024-04 | 1.1B |
| OpenELM 3B | 2024-04 | 3B |
