Camelid
Rust app for offline chat, file work, and coding with GGUF models via desktop, browser, and terminal.
Tested on macOS and LinuxKnown vulnerabilities
Use it
Before you install: known vulnerabilities
pickfit found 6 known high or critical vulnerabilities (10 findings, one per affected package version) in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.
crates:zip 4.6.1zip: Critical Parser Differential & Security Control Bypass via Dual-Header Inconsistencies (Zip Cloaking) Leading to Arbitrary File Overwrite & RCE (GHSA-m665-v7pm-7grj, critical, fixed in 9.0.5)
See 9 more
crates:zip 7.2.0— GHSA-m665-v7pm-7grj (critical), fixed in 9.0.5crates:zip 4.6.1— RUSTSEC-2026-0369 (critical), fixed in 9.0.0crates:zip 7.2.0— RUSTSEC-2026-0369 (critical), fixed in 9.0.0crates:zip 7.2.0— GHSA-9hj8-73fh-9963 (high), fixed in 9.0.0crates:zip 7.2.0— GHSA-hjqx-j4rw-g7xv (high), fixed in 9.0.0crates:zip 4.6.1— GHSA-q7v9-x93c-xqv3 (high), fixed in 9.0.0crates:zip 7.2.0— GHSA-q7v9-x93c-xqv3 (high), fixed in 9.0.0crates:zip 4.6.1— RUSTSEC-2026-0367 (high), fixed in 9.0.0crates:zip 7.2.0— RUSTSEC-2026-0367 (high), fixed in 9.0.0
macOS arm64
You need first
- A GPU is optional
Download DMG from latest release
curl -fsSL -o /tmp/camelid-desktop-macos-arm64.dmg https://github.com/timtoole02/Camelid/releases/latest/download/camelid-desktop-macos-arm64.dmgDownload SHA256 checksum
curl -fsSL -o /tmp/camelid-desktop-macos-arm64.dmg.sha256 https://github.com/timtoole02/Camelid/releases/latest/download/camelid-desktop-macos-arm64.dmg.sha256Mount DMG
mkdir -p ~/Applications && mkdir -p /tmp/camelid-mount2 && hdiutil attach -nobrowse -mountpoint /tmp/camelid-mount2 /tmp/camelid-desktop-macos-arm64.dmg -quietCopy app to ~/Applications and detach
cp -R /tmp/camelid-mount2/"Camelid Desktop.app" ~/Applications/ && hdiutil detach /tmp/camelid-mount2 -quietClear quarantine and verify codesign
xattr -cr ~/Applications/"Camelid Desktop.app" && codesign --verify --deep --strict ~/Applications/"Camelid Desktop.app"
Run camelid pull <model> to download a model, then camelid serve --model <model file> to start the local server.
Linux x86_64
You need first
- A GPU is optional
Download Linux engine archive
mkdir -p ~/apps/camelid && curl -fL -o /tmp/camelid-linux.tar.gz https://github.com/timtoole02/Camelid/releases/download/v0.8.0/camelid-linux-x86_64.tar.gzInstall camelid engine to PATH
tar -xzf /tmp/camelid-linux.tar.gz -C /tmp && mkdir -p ~/.local/bin && cp /tmp/camelid-linux-x86_64/camelid ~/.local/bin/camelid && chmod +x ~/.local/bin/camelid && ~/.local/bin/camelid --version
Check that it works
camelid pullThe output should contain “Download one with:”.
First thing to try
camelid pullRun camelid pull <model> to download a model, then camelid serve --model <model file> to start the local server.
What it does
- Chat with GGUF models on your own machineTested
How to use it
- Download a model with
camelid pull <model>. - Start the server with
camelid serve --model <model file> --no-open --addr <host:port>. - Send a chat request with
curl -s http://<host:port>/v1/chat/completions -H "Content-Type: application/json" -d '<your request JSON>'.
- Download a model with
- Use an OpenAI-compatible APITested
How to use it
- Start the server with
camelid serve --model <model file> --no-open --addr <host:port>. - Check that the model is ready with
curl -fsSL http://<host:port>/v1/health. - Send chat requests to
http://<host:port>/v1/chat/completionsin the OpenAI format.
- Start the server with
- Browse and preview generated filesNot tested
- Write code in chat and review editsNot tested
How far pickfit got
macOS arm64
- Installs
- Opens
- Not used yet
- Works offline
Linux x86_64
- Installs
- Starts
- 2 of 4 features work
- Works offline
Other systems
Windows: the project says it runs there; pickfit hasn’t tried it.
Good for
- chat with local models with markdown replies
- preview and download generated files
- code in a local project with reviewed edits
- do web research with reply sources
- search local document library
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
macOS arm64
It opens to its main screen
- Replayed from scratch
- Checked on 1 Nov 2026
- Version 0.8.0
When pickfit opened it, its main screen rendered. That shows it installs and starts; pickfit did not use any of its features. The launch passed again with the network off.
Differences the test machine hit
- README: curl -fsSL https://raw.githubusercontent.com/timtoole02/Camelid/main/scripts/get-desktop-macos.sh | bash installs to /Applications
In the test: Standard user cannot write to /Applications; installed to ~/Applications via manual DMG mount (mkdir -p ~/Applications, hdiutil attach, cp -R, xattr -cr, codesign --verify) using same DMG URL the script uses - README: No mention of quarantine handling
In the test: App is ad-hoc signed not notarized; curl download avoids quarantine but xattr -cr still required to verify and launch cleanly
Linux x86_64
Installs and starts
- Replayed from scratch
- Works offline
- Checked on 1 Nov 2026
- Version camelid v0.8.0
Differences the test machine hit
- README: Download desktop app for Windows/macOS/Linux platforms
In the test: Linux asset camelid-linux-x86_64.tar.gz contains only headless camelid engine + CUDA libs; no desktop window app for Linux (desktop bundles are Windows zip/exe and macOS DMG only) - README: camelid serve --model models/Llama-3.2-3B-Instruct-Q8_0.gguf and chat model Llama 3.2 3B Instruct
In the test: used catalog tiny model gemma3_270m_it_q8_0 (278 MB, models/gemma-3-270m-it-Q8_0.gguf) and model id Gemma-3-270M-It from /v1/health - README: Read loaded model ID from GET /v1/models
In the test: GET /v1/models returned empty list while /v1/health reported active_model_id Gemma-3-270M-It and generation_ready true