ChatWeb can crawl web pages, read PDF, DOCX, TXT, and extract the main content, then answer your questions based on the content, or summarize the key points.
App showcasing multiple real-time diffusion models pipelines with Diffusers
关键参数与规格
关键参数与规格
参数
值
语言
Swift
类别
Applications
子类别
Personal,Wrappers
关键词
Client integration, LocalAI, Memory management, Tool use
星标数
915
分叉数
15
贡献者
2
创建日期
2026-05-29
更新日期
2026-10-12
1 天星标数
0
7 天星标数
-1
排名
12,669
上次排名
12,585
排名变化
-84
7 天星标排名
17,443
上次 7 天星标排名
17,413
7 天星标排名变化
-30
总星标排名
11,915
上次总星标排名
11,892
总星标排名变化
-23
README 摘录
DS4 Control A macOS menu bar pane for **DeepSeek V4** and **V4. It launches, supervises, and monitors a local ds4 server, lets you pick **V4. 1 Flash**, **V4 Pro (0813)**, or **V4 Flash (0731)** with up to **1M** context, and shows resource use. **Launch Pi, Claude Code or BYOC (Bring Your Own CLI) for local agentic coding. **Pro / Flash selector** with a RAM feasibility checks. **Model downloads** via a built-in native parallel downloader, with a live progress bar and
resume across restarts. **Mini resource widgets**: unified memory, GPU, power, and CPU, sampled on a timer. **Launch Claude Code or Pi** to plan, write, maintain or refactor code. **1M Context** configurable in settings. **Launch on macOS Startup** What it is **not**: No model search or registry browsing. **Auth (optional):** the model repository is public, so no token is required for normal use. RAM feasibility DeepSeek V4 is memory-hungry so DS4 Control gates feasibility before launching. 1 Flash | 41-q2
| ≥ 96 GiB | 341 GiB on disk, ~152 GiB resident main weights + ~189 GiB disk-only Engram. SSD streaming engages automatically on 96–255 GiB (slow: nearly every routed expert streams from disk); full residency on ≥ 256 GiB. 1 Flash | 41-q4 | ≥ 256 GiB | 483 GiB on disk, ~294 GiB resident main weights. SSD streaming on 256–511 GiB; full residency on ≥ 512 GiB. | | V4 Flash (0731) | q4-imatrix | ≥ 256 GiB | Standard. | | V4 Flash (0731) | q2-imatrix | 96 GiB minimum | 96
–127 GiB requires raising the Metal wired limit (see in-app help). Coding Agents It’s suggested to follow the ds4 coding agent setup guide to configure your OpenCode/Claude/Codex/Pi as you prefer. Build & Run For development: To produce a distributable bundle: This builds a release binary and assembles . Signing auto-detects your **Apple Development** identity via and signs the bundle with it. If no Apple Development identity is installed, it falls back to **ad-hoc** signing (the
app runs locally but is not distributable). To sign with your own key: Install an Apple Development certificate (Xcode → Settings → Accounts → Manage Certificates → **+** → Apple Development), **or** Set before running . Three objects do the work, and the SwiftUI layer just observes them: ** ** owns the lifecycle through : it builds the launch arguments, watches stderr for the readiness line, polls for health, and stops gracefully with SIGTERM (SIGKILL fallback). Model weights are fetched by a built-in native parallel downloader (resumable across restarts
). ** ** samples CPU, memory, GPU, and power/ANE via Mach, IOKit, and the private IOReport interface every 2 s, publishing a to the widgets. ** ** turns installed RAM into a variant choice and a budget-derived default context (pure, fully unit-tested). Attribution A big thanks of course to @antirez for antirez/ds4, llama. c and GGML for instrumental foundational work. The resource collectors and widgets are adapted from **mac-resource-monitor**, which in turn credits **macmon** (MIT) for the IOReport power
-sampling approach. The server-supervision pattern is built on the lineage of **mlx-serve**.
A macOS menu bar pane for DeepSeek V4 and V4.1 via dwarfstar.
It launches, supervises, and monitors a local ds4 server, lets you pick V4.1 Flash, V4 Pro (0813), or V4 Flash (0731) with up to 1M context, and shows resource use.
Launch Pi, Claude Code or BYOC (Bring Your Own CLI) for local agentic coding.
Signed with a live Apple Developer ID & notarized by Apple
Quick Install
brew install --cask ds4-control
Features
Start / stop / monitor the local ds4-server child process — spawn, stderr readiness detection, health polling, graceful stop, and crash detection.
Pro / Flash selector with a RAM feasibility checks.
Model downloads via a built-in native parallel downloader, with a live progress bar and resume across restarts.
Mini resource widgets: unified memory, GPU, power, and CPU, sampled on a timer.
Launch Chat to talk to the model.
Launch Claude Code or Pi to plan, write, maintain or refactor code.
1M Context configurable in settings.
Launch on macOS Startup
What it is not:
No model search or registry browsing.
No embedded inference — all inference is delegated to ds4-server.
Dev quick start
antirez/ds4 is vendored as a git submodule at external/ds4:
git submodule update --init --recursive # fetch ds4 into external/ds4
bash scripts/apply-ds4-patches.sh # THINK_MAX prefix (antirez/ds4#635)
make -C external/ds4 -j ds4-server # build the ds4-server binary
DS4_DIR="$PWD/external/ds4" swift run # build + run the dev app against the submodule
Requirements
Apple Silicon
You don't pre-download the model — DS4 Control downloads it for you with a built-in parallel downloader, resumable across restarts.
Auth (optional): the model repository is public, so no token is required for normal use.
RAM — see below.
RAM feasibility
DeepSeek V4 is memory-hungry so DS4 Control gates feasibility before launching.
Variant
Quant
RAM
Notes
V4 Pro (0813)
pro-imatrix
≥ 512 GiB required
Anything below is blocked.
V4.1 Flash
41-q2
≥ 96 GiB
341 GiB on disk, ~152 GiB resident main weights + ~189 GiB disk-only Engram. SSD streaming engages automatically on 96–255 GiB (slow: nearly every routed expert streams from disk); full residency on ≥ 256 GiB.
V4.1 Flash
41-q4
≥ 256 GiB
483 GiB on disk, ~294 GiB resident main weights. SSD streaming on 256–511 GiB; full residency on ≥ 512 GiB.
V4 Flash (0731)
q4-imatrix
≥ 256 GiB
Standard.
V4 Flash (0731)
q2-imatrix
96 GiB minimum
96–127 GiB requires raising the Metal wired limit (see in-app help).
Performance
Measured single-stream generation throughput on a Mac Studio M3 Ultra (512 GiB):
Model
Throughput
V4 Pro (0813)
~14 tok/s
V4 Flash (0731)
~35 tok/s
Varies with context length, prompt, and the Metal wired limit.
Coding Agents
It’s suggested to follow the ds4 coding agent setup guide to configure your OpenCode/Claude/Codex/Pi as you prefer.
Build & Run
For development:
swift run
To produce a distributable bundle:
bash build.sh
This builds a release binary and assembles DS4 Control.app.
First run: open Settings (the gear in the popup) and set the ds4 directory — the folder that contains ds4-server.
Signing
build.sh auto-detects your Apple Development identity via security find-identity and signs the bundle with it. If no Apple Development identity is installed, it falls back to ad-hoc signing (the app runs locally but is not distributable).
To sign with your own key:
Install an Apple Development certificate (Xcode → Settings → Accounts → Manage Certificates → + → Apple Development), or
Set DS4_SIGN_IDENTITY="Apple Development: …" before running build.sh.
How it works
DS4 Control is a single Swift binary — no embedded inference and no second process language. Three @MainActor objects do the work, and the SwiftUI layer just observes them:
SupervisorService owns the ds4-server lifecycle through Foundation.Process: it builds the launch arguments, watches stderr for the listening on http:// readiness line, polls GET /v1/models for health, and stops gracefully with SIGTERM (SIGKILL fallback). Model weights are fetched by a built-in native parallel downloader (resumable across restarts).
MetricsManager samples CPU, memory, GPU, and power/ANE via Mach, IOKit, and the private IOReport interface every 2 s, publishing a SystemSnapshot to the widgets.
Feasibility turns installed RAM into a variant choice and a budget-derived default context (pure, fully unit-tested).
Attribution
A big thanks of course to @antirez for antirez/ds4, llama.c and GGML for instrumental foundational work.
The resource collectors and widgets are adapted from mac-resource-monitor, which in turn credits macmon (MIT) for the IOReport power-sampling approach.
The server-supervision pattern is built on the lineage of mlx-serve.