Models in the app
Running models locally
How GGUF, MLX, ExecuTorch, Core ML, and Apple Foundation Models differ, including the Noema 1.5 4B recommendations in 4.2.
On this page
Noema 1.5 4B Deep and Fast
Explore recommends Noema 1.5 4B Deep for longer math and coding reasoning and Fast for brief everyday reasoning. Both have GGUF and MLX variants and a model context window of up to 262K tokens.
A model’s maximum context is not a promise that it fits in your device’s memory. Choose the format, quantization, and context Noema recommends for the current hardware. See the Noema 1.5 4B model page for evaluation details, and Run Noema models to use the same weights outside the app.
Local runtime choices
| Runtime | Best fit | What to know |
|---|---|---|
| GGUF | Broad compatibility and detailed tuning | Flexible quantizations, context controls, projectors, and advanced runtime options. |
| MLX | Apple-silicon optimization | Efficient Apple-native execution with a more opinionated settings surface. |
| ExecuTorch | Packaged mobile deployments | Compatibility and available controls depend on the exported model bundle. |
| CML / Core ML | Apple neural-engine and packaged model workflows | Dependencies and supported capabilities are model-specific. |
| AFM | Apple’s built-in Foundation Model | Availability depends on device and OS; it is activated, not downloaded like a model file. |
Choose by fit, not parameter count alone
- RAM fit includes model weights, key-value cache, context length, runtime overhead, and vision or audio dependencies.
- A lighter quantization reduces memory use but can change quality and speed.
- Long context can consume more memory than expected even with a small model.
- Vision, tool calling, reasoning, and audio support are separate capabilities; inspect badges and model notes before downloading.
Load and run a model
- Open Explore and choose a compatible model and quantization.
- Review license, provenance, capability badges, dependencies, and estimated fit.
- Download the model and any required projector or companion files.
- Open Stored, review its runtime settings, and load it.
- Select it in Chat and monitor the context gauge and runtime receipt.
Performance and energy
Use a runtime preset instead of enabling system Low Power Mode as a model-tuning strategy. Battery Saver reduces the workload through Noema’s own settings; Balanced is a good default; Max Speed favors throughput when heat and power use are acceptable.
- Reduce context length before assuming the model is too large.
- Close memory-heavy apps and avoid loading multiple large local models unless the fit estimate allows it.
- Benchmark on the device where the model will actually run.