Core ML Model Zoo
Collection
PyTorch models converted to Core ML for on-device inference on iPhone, iPad and Mac. • 46 items • Updated • 1
Nitro-E (4-Step) — Core ML
AMD, 2025
AMD's 304M E-MMDiT text-to-image model (Oct 2025). 4-step distilled variant, 512×512. Llama 3.2 1B text encoder + E-MMDiT denoiser + DC-AE VAE decoder. ~1.04 GB bundled after INT4/INT8 palettization. ~2–3 s / image on iPhone 15+.
Core ML conversion of amd/Nitro-E for on-device inference on iPhone, iPad and Mac. Converted with coremltools; the packages are stateless, so all sequencing and buffering lives in your Swift code.
| Task | text to image |
| Upstream | amd/Nitro-E |
| Packages | 3 |
| Download size | 987 MB |
| Minimum iOS | 18.0 |
| Peak RAM | ~2500 MB |
Files
| File | Size | Compute units | SHA-256 |
|---|---|---|---|
NitroE_TextEncoder.mlpackage.zip |
545 MB | cpuAndNeuralEngine |
9b366b29d790ab98… |
NitroE_EMMDiT.mlpackage.zip |
283 MB | cpuAndNeuralEngine |
93a7ed971c5c419d… |
NitroE_VAEDecoder.mlpackage.zip |
153 MB | cpuAndNeuralEngine |
4837023736d82b49… |
Llama3Vocab.json |
2 MB | - |
f8f40517934d6f5d… |
Llama3Merges.txt |
3 MB | - |
0cd100e0ab7dbd83… |
| Total | 987 MB |
compute_units is not a suggestion -- it is the configuration the conversion was verified against. Moving a package to a different compute unit can silently change the numerics (FP16 attention overflow) or crash on the GPU.
Download
hf download mlboydaisuke/coreml-zoo --include "nitroe/*" --local-dir ./nitroe
unzip './nitroe/nitroe/*.zip' -d ./nitroe
Use in Swift
import CoreML
let config = MLModelConfiguration()
config.computeUnits = .cpuAndNeuralEngine // as converted — see the table above
// Unzip the .mlpackage, drop it into your Xcode target and Xcode compiles it
// at build time:
let model = try NitroE_TextEncoder(configuration: config)
// ...or compile a downloaded .mlpackage at runtime:
let compiled = try await MLModel.compileModel(at: mlpackageURL)
let model = try MLModel(contentsOf: compiled, configuration: config)
This model is split into 3 Core ML packages that are driven in sequence from Swift. Load them one at a time, copy the outputs out of the
MLMultiArraybuffers and release each model before loading the next — two large Core ML models resident at once will OOM on an iPhone.
Demo
- Sample app —
sample_apps/NitroEDemo, a standalone SwiftUI project. - Models Zoo — this model is downloadable and runnable inside the Models Zoo app on the App Store, no build required.
Conversion
- Script:
convert_nitro_e_emmdit.py - Pitfalls hit during conversion (FP16 overflow, ANE buffer limits, stride handling):
docs/coreml_conversion_notes.md - Model index: CoreML-Models
License
The conversion inherits the upstream license: MIT (Nitro-E) + Llama 3.2 Community License (text encoder). See https://huggingface.co/amd/Nitro-E.
Nitro-E itself is MIT; the bundled text encoder is Llama 3.2 and carries the Llama 3.2 Community License.
Credits
- Upstream authors: amd/Nitro-E, 2025
- Core ML conversion: john-rocky (Daisuke Majima)
- Downloads last month
- 22
Model tree for mlboydaisuke/Nitro-E-CoreML
Base model
amd/Nitro-E