---
library_name: coreai
license: apache-2.0
base_model: Qwen/Qwen3-4B
tags:
- coreai
- apple
- aimodel
- apple-silicon
---

Core AI is Apple's on-device ML runtime in iOS 27 / macOS 27 and the successor to Core ML: PyTorch models are exported with Apple's `coreai-torch` (LLMs: `coreai.llm.export`) into `.aimodel` bundles that run on the GPU or the Neural Engine, e.g. Qwen3-8B 4-bit decodes at 94 tok/s on an M4 Max GPU, MLX 90 under the same protocol ([apple-silicon-llm-bench](https://github.com/john-rocky/apple-silicon-llm-bench), macOS 27 beta 26A5353q, 2026-06-11).

<!-- gen-cards:devicemark begin (managed by scripts/gen-cards + tools/devicemark_row.py — edit cards.json, not this block) -->
This model has no row on [DeviceMark](https://devicemark.github.io/), the on-device LLM leaderboard.
<!-- gen-cards:devicemark end -->

# Qwen3-4B — official Apple Core AI exports

Pre-converted **`.aimodel` bundles from Apple's official
[coreai-models](https://github.com/apple/coreai-models) export recipe — unmodified**,
with the exact environment, hashes, and measured performance published.

```bash
uv run coreai.llm.export qwen3-4b              # macOS
uv run coreai.llm.export qwen3-4b --platform iOS
```

<!-- gen-cards:use-it begin id=qwen3-4b (managed by scripts/gen-cards — edit cards.json / QuickStart.swift, not this block) -->
## Use it

**New to Core AI? [Start with CoreAIKit 0.7.3](https://github.com/john-rocky/coreai-kit#readme).** Follow its requirements and first-run steps for `qwen3-0.6b`, then open the same release's [ChatDemo](https://github.com/john-rocky/coreai-kit/tree/0.7.3/Examples/ChatDemo). The README records the tested OS/SDK and download size; model and device coverage is stated per example.

⚡ **One line** — this model is the default behind the kit's task op
(`import CoreAIOps`; no session, no model plumbing, downloads on first use):

```swift
let tldr = try await CoreAI.summarize(text)
```

Every op, one shape — [Cookbook](https://github.com/john-rocky/coreai-kit/blob/0.7.3/docs/COOKBOOK.md).

▶️ **Run it (source)** — the [ChatDemo runner](https://github.com/john-rocky/coreai-kit/tree/0.7.3/Examples/ChatDemo)
(GUI + CLI, one app for every chat model in the catalog):

```bash
git clone --branch 0.7.3 --depth 1 https://github.com/john-rocky/coreai-kit
export DEVELOPER_DIR=/Applications/Xcode-27.0.0-RC.app/Contents/Developer
open -a /Applications/Xcode-27.0.0-RC.app coreai-kit/Examples/ChatDemo/ChatDemo.xcodeproj
# → Run, then pick "Qwen3 4B" in the model picker

# agents / headless (macOS):
cd coreai-kit/Examples/ChatDemo
swift run -c release chat-cli --model qwen3-4b --prompt "What can you do, offline?"
```

Use Xcode build **27A266a** from the release's `.xcode-pin`; adjust the app path if your installation is named differently.

💻 **Build with it** — complete; the glue is kit API, copy-paste runs:

```swift
import CoreAIKit

let id = "qwen3-4b"
let chat: ChatSession
if id == "qwen3-0.6b" {
    // Freeze the release starter; other selections retain the live catalog's
    // model-specific dispatch (including paired Gemma bundles).
    guard let model = ModelCatalog.builtin.entry(id: id)?.modelID else {
        throw CoreAIKitError.modelNotAvailableOnPlatform(id: id)
    }
    chat = try await ChatSession(model: model)
} else {
    chat = try await ChatSession(catalog: "qwen3-4b")
}
let reply = try await chat.respond(to: prompt)
// reply: the answer, generated fully on-device
```

The take-home is [`Examples/ChatDemo/Sources/QuickStart.swift`](https://github.com/john-rocky/coreai-kit/blob/0.7.3/Examples/ChatDemo/Sources/QuickStart.swift)
— this exact code as one typed function, no UI; the CLI is an argument shell over it, and
the GUI drives the same `ChatSession` across turns for its transcript.
Multi-turn? Hold the `ChatSession` and call `respond(to:)` per turn — it keeps the
conversation history; `streamResponse(to:)` yields tokens as they decode.

**Integration checklist**

- SPM: `https://github.com/john-rocky/coreai-kit` (exact **0.7.3**) → product **CoreAIKit**
- Info.plist: none needed
- Entitlements (iOS): `com.apple.developer.kernel.increased-memory-limit`
- First run downloads the model — ~2,279 MB (Mac) / ~2,502 MB (iPhone) — then it loads from the
  local cache (Application Support; progress via the `downloadProgress` callback)
- Measure in Release — Debug is ~3× slower on per-token host work
<!-- gen-cards:use-it end -->

## Why pre-converted bundles?

1. **The conversion needs a big-RAM Mac** (the 20B export was done on 128 GB);
   running only needs enough RAM to mmap the artifact.
2. **An `.aimodel` is a build artifact, not a pure function of the recipe** — the
   same export command produced a 2.2× slower artifact across the macOS 26 → 27β
   boundary ([forensics](https://github.com/john-rocky/apple-silicon-llm-bench/blob/main/methodology/coreai-export-lowering.md)).
   Hosted artifacts + hashes are the reproducible ground truth; every bundle here
   is exactly the one measured in
   [apple-silicon-llm-bench](https://github.com/john-rocky/apple-silicon-llm-bench).

## Bundles & integrity

| Bundle | Contents | SHA-256 (`main.mlirb`) |
|---|---|---|
| `macos/` | macOS dynamic, int4 | `e9d1e9e49e70e7abe0c9a24062603a827483ed6ffb9ac4f244c553156c8ce5e7` |
| `ios/` | iOS static ctx4096, mixed 4/8-bit palettized | `a1c45800117f2a0a00df5cd4196485a7ea6bc9d894b3d4cac3f3aa032a1c0a89` |

## Measured (Apple's official `llm-benchmark`, greedy)

| Bundle | Protocol | Decode tok/s | Prefill | Load (warm) |
|---|---|---:|---:|---:|
| macos | M4 Max, 512p/1024g | 145.4 | 1,635 | 0.36 s |
| ios (ANE, h18p) | iPhone 17 Pro, 512p/1024g | 13.2 | 546 | 0.46 s (cold spec ≈194 s) |

## Export environment

- macOS 27.0 beta (build 26A5353q) · Xcode 27.0 (27A5194q)
- `coreai-core 1.0.0b1` · `coreai-torch 0.4.0` · `coreai-opt 0.2.0` · `torch 2.9.0`
- apple/coreai-models @ `b1cb71b` (export code identical to upstream `0c1055f`)

## Run it

```bash
# CLI (from a coreai-models checkout)
swift run -c release llm-runner --model <downloaded-bundle-dir> --prompt "Hello"
swift run -c release llm-benchmark --model <downloaded-bundle-dir>
```

Or chat with it in [CoreAIChatMac](https://github.com/john-rocky/coreai-samples)
(point "Choose Models Folder…" at the download directory).

iOS static bundles must be AOT-compiled before device use:
`xcrun coreai-build compile <ir>.aimodel --platform iOS --preferred-compute neural-engine --architecture h18p`
(h18p = iPhone 17 Pro), then set `metadata.json` `assets.main` to the `.aimodelc`.



---
Maintained alongside [coreai-model-zoo](https://github.com/john-rocky/coreai-model-zoo)
(community models) and [coreai-samples](https://github.com/john-rocky/coreai-samples) (apps).

<!-- funnel:v1 -->

---

**More models in this format:** [Core AI Model Zoo](https://huggingface.co/collections/mlboydaisuke/core-ai-model-zoo-6a7ff330f753e8dcae04671a) — 75 models, each with the recipe that produced it.

**Want a different model on-device?** [Open a request](https://github.com/john-rocky/on-device-requests) — free, open weights only; the export and its measured numbers get published publicly.

<!-- /funnel:v1 -->