chimera
Single static binary and library for local text, audio, and image inference via ggml.
Tested on Linux
Use it
Linux x86_64
You need first
- System packages:
OpenSSL
Download prebuilt Linux x86_64 CPU release tarball and install to ~/.local/bin
mkdir -p ~/.local/bin /tmp/chimera-dl2 && curl -fL -o /tmp/chimera-dl2/chimera.tar.gz https://github.com/shakfu/chimera/releases/download/0.7.0/chimera-0.7.0-linux-x86_64.tar.gz && tar -xzf /tmp/chimera-dl2/chimera.tar.gz -C /tmp/chimera-dl2 && install -m 755 /tmp/chimera-dl2/chimera ~/.local/bin/chimera
Check that it works
chimera --helpThe output should contain “SUBCOMMANDS:”.
First thing to try
chimera infoRun chimera info to check the install and see what the tool supports.
What it does
These come from the README; pickfit didn’t check them one by one.
- Generate text and chat with a local modelNot tested
- Transcribe speech to textNot tested
- Generate images from text promptsNot tested
- Serve an OpenAI-compatible HTTP APINot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- Produces output
- Works offline
macOS and Windows: the project says it runs there; pickfit hasn’t tried it.
Good for
- Generate text with a local LLM
- Transcribe a WAV file offline
- Generate images from text prompts
- Serve an OpenAI-compatible HTTP API locally
An alternative to Ollama, LM Studio and Jan.
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
Linux x86_64
It produces model output
- Replayed from scratch
- Works offline
- Checked on 30 Oct 2026
- Version 0.7.0
Differences the test machine hit
- README: make build (then optionally make install) with OpenSSL installed via apt
In the test: Used the prebuilt CPU asset chimera-0.7.0-linux-x86_64.tar.gz from GitHub releases (tarball contains a single bare file named 'chimera'); installed it to ~/.local/bin/chimera with install -m 755. Departed from ranked source candidates because the box has no compiler, cmake, make, or OpenSSL headers…