Watch the 0.4.1 Mac demo:
Qwen3 0.6B chat → VoxCPM 0.5B speech. Recorded on a Mac Studio M4 Max with the
public exact 0.4.1 examples and Xcode 27 beta 5 (27A5237l). Builds and model downloads
are omitted; the video shows cached runs. The reproduction record
includes commands, model pins, and recording details. The separate
release evidence
includes the empty-cache first download, two-turn chat, and Japanese streaming checks.
Earlier real-device captures (July 2026; iPhone 17 Pro / M4 Max). These illustrate other capabilities and are not 0.4.1 validation evidence. Captions lead with the one-line call where a task op covers it; each cell links to the kit example — or zoo app — that runs the same model. (Media lives in coreai-assets, so cloning this repo stays fast.)
![]() |
![]() |
![]() |
ChatSession — chat, Youtu-LLM-2BChatDemo |
CoreAI.transcribe — Whisper v3 turboTranscribe |
CoreAI.transcribeMeeting — Sortformer + ParakeetMeeting |
![]() |
![]() |
|
KitVisionModel — screen VLM, Holo2-4BVLChat |
Repo agent — FastContext-4B zoo CoreAIChat |
CoreAI.detect — RF-DETR nano, no NMSDetectCamera |
![]() |
![]() |
![]() |
| Segmentation — SAM 3 zoo |
CoreAI.estimateDepth — Depth Anything 3DepthCamera |
CoreAI.upscale — AdcSR ×4UpscaleDemo |
![]() |
![]() |
![]() |
CoreAI.redact — PII, GLiNER2InfoExtract |
CoreAI.read — GLM-OCR 0.9B, ~4 s/pageReadDoc |
1.58-bit ternary — BitCPM-8B in ~2.1 GB zoo CoreAIChat |
![]() |
![]() |
| Text→image — GLM-Image zoo CoreAIImageGen |
In-context edit — FLUX.2 klein zoo CoreAIImageGen |
![]() |
![]() |
| Text→video — LTX-Video 2B zoo CoreAIVideo |
Photo→3D splat — TripoSplat zoo TripoSplatMac |
![]() |
![]() |
Diffusion LLM (parallel denoise) — LLaDA-8BDiffuseChat |
CoreAI.read — MinerU2.5, doc→MarkdownReadDoc |

CoreAI.forecast — TimesFM 2.5, ~25 ms/forecast on iPhone · Forecast

Agentic coding — Ornith-1.0-9B on M4 Max · zoo CoreAIChatMac