pickfit

BrowseLocal AI tools

Lattice

Pure Rust inference engine for running transformer models locally on Apple Silicon and Linux.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Rust 1.93+
  • A GPU is optional
  • At least 8 GB of RAM
  1. Download prebuilt lattice binary release

    mkdir -p ~/.local/bin /tmp/lattice-dl && cd /tmp/lattice-dl && curl -fLO "https://github.com/ohdearquant/lattice/releases/download/v0.9.0/lattice-0.9.0-x86_64-unknown-linux-gnu.tar.gz" && curl -fLO "https://github.com/ohdearquant/lattice/releases/download/v0.9.0/lattice-0.9.0-x86_64-unknown-linux-gnu.tar.gz.sha256"
  2. Verify checksum and list tarball

    cd /tmp/lattice-dl && sha256sum -c lattice-0.9.0-x86_64-unknown-linux-gnu.tar.gz.sha256
  3. Clean reinstall ending in help check

    cd /tmp/lattice-dl && tar -xzf lattice-0.9.0-x86_64-unknown-linux-gnu.tar.gz && install -m 0755 lattice-0.9.0-x86_64-unknown-linux-gnu/lattice ~/.local/bin/lattice && lattice --help

Check that it works

lattice --help

The output should contain “Usage: lattice <COMMAND>”.

Run lattice --help to see the available commands.

What it does

  • Chat with a local model
    Not tested
  • Serve an OpenAI-compatible chat API
    Not tested
  • Generate embeddings with 9 supported models
    Not tested
  • Quantize models to Q4 or Q8
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 0 of 4 features work
  4. Works offline

macOS: the project says it runs there; pickfit hasn’t tried it.

Good for

  • run interactive chat with a local model
  • serve OpenAI-compatible chat completions locally
  • quantize models to Q4 or QuaRot

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

Installs and starts

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026

Differences the test machine hit

  • README: cargo install lattice-serve --bin lattice --features f16 (requires Rust 1.93+)
    In the test: used prebuilt release tarball lattice-0.9.0-x86_64-unknown-linux-gnu.tar.gz (verified sha256, installed to ~/.local/bin)
  • README: GitHub releases ship lattice-<version>-<target>.tar.gz
    In the test: only v0.9.0 has prebuilt Linux x86_64 assets; releases up to v0.14.0 ship none, so the binary lags current crate versions
  • README: README documents chat/serve usage without stating version-flag support
    In the test: top-level `lattice --version` errors (exit 2); `lattice --help` works and lists chat/serve/doctor/prune-score

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.