mlboydaisuke/Qwen3-VL-4B-CoreAI

Qwen3-VL 4B — Core AI (.aimodel)

Qwen/Qwen3-VL-4B-Instruct converted to Apple Core AI (.aimodel, iOS 27 / macOS 27): image+text → text fully on the GPU via Apple's coreai-pipelined engine, zero custom kernels. The 4B sibling of the Qwen3-VL 2B port — it drops onto the same recipe with zero code changes (the model overlay and exporter are fully config-driven).

Part of the CoreAI-Model-Zoo; full card with the conversion design: zoo/qwen3-vl.md.

Use it

▶️ Run it (source) — the VLChat runner (GUI + CLI, one app for every vision-language model in the catalog):

git clone https://github.com/john-rocky/coreai-kit
open coreai-kit/Examples/VLChat/VLChat.xcodeproj
# → Run, then pick "Qwen3-VL 4B" in the model picker

# agents / headless (macOS):
cd coreai-kit/Examples/VLChat
swift run vlchat-cli --model qwen3-vl-4b --image sample.jpg --prompt "What is in this image?"

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

import CoreAIKit
import FoundationModels

let vlm = try await KitVisionModel(catalog: "qwen3-vl-4b")
let session = LanguageModelSession(model: vlm)
let image = try ImageFile.load(imageURL)  // any image file → CGImage + EXIF orientation
let reply = try await session.respond(to: Prompt {
    prompt
    Attachment(image.cgImage, orientation: image.orientation)
})
// reply.content: the answer about the image, generated fully on-device

The take-home is Examples/VLChat/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 KitVisionModel(catalog:) behind a LanguageModelSession. Multi-turn about the same image? Hold the LanguageModelSession and call respond(to:) per turn. The photo picker / file chooser is your app's own chrome — ImageFile.load (kit API) turns any image file into model input.

Integration checklist

• SPM: https://github.com/john-rocky/coreai-kit → product CoreAIKit
• Info.plist: NSPhotoLibraryUsageDescription — only if you use PhotosPicker
• Entitlements (iOS): com.apple.developer.kernel.increased-memory-limit
• First run downloads the model — 5.9 GB (Mac) / 5.9 GB (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

Measured

platform	prefill tok/s	decode tok/s	numerics
M4 Max (macOS 27 beta)	93.3	92.2	torch ladder vs fp32-HF (positions exact, vision cos 1.000, 36/36 layers cos 1.000, decode 16/16) + engine ≡ python 24/24 on the 211-tok multimodal prompt
iPhone 17 Pro (iOS 27 beta)	10–15	14.0 cool → ~8.5 sustained	nat 24/24 + multimodal oracle 24/24 × 3 runs, token-identical to Mac

Decode is bandwidth-bound: the 4.7 GB int8hu decoder reads ~4.7 GB/token, so it runs at roughly half the 2B's rate. On iPhone the read is heavy enough to thermally throttle — ~14 tok/s from a cool start, settling to ~8.5 under sustained decode. Device cold load 52.7 s (on-device GPU specialization, no AOT), warm 8–9 s; needs the increased-memory entitlement (4.7 GB class).

Files

path	what	size
gpu-pipelined/qwen3_vl_4b_instruct_decode_int8hu_s1/	text decoder LanguageBundle (SHIP: int8 per-block-32 body + untied absmax int8 head; tokenizer + metadata included)	4.7 GB
gpu-pipelined/qwen3_vl_4b_instruct_vision/	fixed-grid vision encoder (448×448 → 196 tokens + DeepStack), fp16	0.79 GB

How it works (short version)

The text-only pipelined engine carries the VLM through an id-space trick — no engine code changes beyond the published static-inputs patch:

• the vision encoder runs once per image; its embeddings ride 4 static graph inputs (rewritable owned MTLBuffers),
• the prompt's <|image_pad|> ids become extension ids vocab + slot; the graph selects text-table vs image-embed rows per token and applies the three DeepStack adds the same way,
• interleaved M-RoPE is derived in-graph from (ids, position) alone — image tokens self-locate, text tokens use a host-set shift; with zero embeds the same bundle is a plain Qwen3 text LLM.

Numerics are gated the zoo way: fp32-HF oracle → torch ladder (position formula exact vs get_rope_index, 36/36 layers) → .aimodel GPU → engine ≡ python 24/24 → device 24/24.

Run it

See the zoo's apps/CoreAIChat (iOS) Qwen3-VL mode and the run contract (S=1 prefill, COREAI_CHUNK_THRESHOLD=1, never engine.warmup()) in knowledge/pipelined-engine.md.

Conversion is reproducible from the zoo: conversion/export_qwen3_vl_pipelined.py int8hu --hf-id Qwen/Qwen3-VL-4B-Instruct.

License

Apache-2.0 (inherited from Qwen3-VL-4B-Instruct). Conversion code BSD-3-Clause (zoo repo).