Skip to content
Back to search

llmfit

Hundreds of models & providers. One command to find what runs on your hardware.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/AlexsJones/llmfit with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/AlexsJones/llmfit'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/alexsjones--llmfit/badge.svg)](/listings/alexsjones--llmfit)

HTML

<a href="/listings/alexsjones--llmfit"><img src="/api/listings/alexsjones--llmfit/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

Windows

scoop install llmfit

If Scoop is not installed, follow the [Scoop installation guide](https://scoop.sh/).

macOS / Linux

Homebrew

Prebuilt binary (recommended, works on all macOS/Linux versions):

brew install AlexsJones/llmfit/llmfit

Or from the homebrew-core formula, which builds from source on macOS versions without a bottle:

brew install llmfit

MacPorts

port install llmfit

Quick install

curl -fsSL https://llmfit.axjns.dev/install.sh | sh

Downloads the latest release binary from GitHub and installs it to `/usr/local/bin` (or `~/.local/bin` if no sudo).

**Install to `~/.local/bin` without sudo:**

curl -fsSL https://llmfit.axjns.dev/install.sh | sh -s -- --local

uv / pip

To install or update llmfit:

uv tool install -U llmfit

To run without installing:

uvx llmfit

You can also install llmfit as a Python package in the normal way with tools such as pip or uv.

Pre-built Binaries

Download release binaries for Linux, macOS, and Windows directly from the [GitHub Releases](https://github.com/AlexsJones/llmfit/releases) page. Windows binaries are signed only when that release's complete `sign-windows` job succeeds, including signing, repackaging, artifact replacement, and checksum upload; a release may still publish an unsigned Windows artifact if signing is skipped or fails. Verify the executable signature if you require a signed binary.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 324 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # llmfit
  2. <p align="center">
  3. <img src="assets/icon.svg" alt="llmfit icon" width="128" height="128">
  4. </p>
  5. <p align="center">
  6. <b>English</b> ·
  7. <a href="README.zh.md">中文</a> ·
  8. <a href="README.ja.md">日本語</a>
  9. </p>
  10. <p align="center">
  11. <a href="https://github.com/AlexsJones/llmfit/actions/workflows/ci.yml"><img src="https://github.com/AlexsJones/llmfit/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
  12. <a href="https://crates.io/crates/llmfit"><img src="https://img.shields.io/crates/v/llmfit.svg" alt="Crates.io"></a>
  13. <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="License"></a>
  14. <a href="https://about.signpath.io"><img src="https://img.shields.io/badge/SignPath-signed-brightgreen?logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIxNiIgaGVpZ2h0PSIxNiIgZmlsbD0id2hpdGUiIHZpZXdCb3g9IjAgMCAxNiAxNiI+PHBhdGggZD0iTTEwLjA2NyA0LjU2N2wtNC43MzQgNC43MzMtMS40LTEuNGExIDEgMCAwIDAtMS40MTQgMS40MTRsMi4xIDIuMWExIDEgMCAwIDAgMS40MTQgMGw1LjQ0LTUuNDRhMSAxIDAgMCAwLTEuNDE0LTEuNDE0eiIvPjwvc3ZnPg==" alt="Signed with SignPath"></a>
  15. </p>
  16. <p align="center">
  17. <a href="https://trendshift.io/repositories/21325?utm_source=repository-badge&amp;utm_medium=badge&amp;utm_campaign=badge-repository-21325" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/repositories/21325" alt="AlexsJones%2Fllmfit | Trendshift" width="250" height="55"/></a>
  18. </p>
  19. Find out which open-source Large Language Models (LLMs) your hardware can comfortably run. `llmfit` inspects your CPU, system RAM, GPU(s), VRAM, and accelerator configuration to recommend models across popular quantizations.
  20. **📊 New: benchmark & share — real numbers from your machine, better estimates for everyone.** Download a model, serve it, and measure real tok/s on your hardware — then contribute the results back to the project as a PR, straight from the TUI. No `gh` CLI, no third-party account. Every run is saved locally first, your own measurements replace estimates in the fit table, and each merged submission ships in the next release: anyone on identical hardware gets measured `✓` numbers before they ever run a benchmark. [Follow the step-by-step benchmarking guide →](docs/benchmarking.md)
  21. ![llmfit demo: searching for a model, simulating different hardware, and planning a deployment](assets/demo.gif)
  22. ## Features
  23. - **Hardware Auto-Detection**: Detects CPU cores, system RAM, available discrete/integrated GPUs, VRAM, and unified memory architecture (NVIDIA CUDA, Apple Silicon, AMD ROCm, Intel OneAPI).
  24. - **Model Compatibility Engine**: Analyzes model parameter counts, context lengths, and quantization formats (GGUF, AWQ, GPTQ, EXL2) to project memory footprints and tokens-per-second performance.
  25. - **Interactive TUI & Web Dashboard**: Choose between a lightweight, zero-dependency terminal interface or a feature-rich web dashboard.
  26. - **REST API Endpoint**: Exposes standard HTTP JSON endpoints (`/api/v1/system`, `/api/v1/models`) for integration into orchestrators, dashboards, and automated deployment pipelines.
  27. - **Multi-Platform Support**: macOS (Apple Silicon & Intel), Linux (x86_64 & ARM64), and Windows (x86_64).
  28. - **Hundreds of models & providers. One command to find what runs on your hardware.**
  29. A terminal tool that right-sizes LLM models to your system's RAM, CPU, and GPU. Detects your hardware, scores each model across quality, speed, fit, and context dimensions, and tells you which ones will actually run well on your machine.
  30. Ships with an interactive TUI (default) and a classic CLI mode. Supports multi-GPU setups, MoE architectures, dynamic quantization selection, speed estimation, and local runtime providers (Ollama, llama.cpp, MLX, Docker Model Runner, LM Studio).
  31. ---
  32. ## Sister projects
  33. - [sympozium](https://github.com/sympozium-ai/sympozium/) — managing agents in Kubernetes.
  34. - [llmserve](https://github.com/AlexsJones/llmserve) — a simple TUI for serving local LLM models. Pick a model, pick a backend, serve it.
  35. - [llama-panel](https://github.com/AlexsJones/llama-panel) — a native macOS app for managing local llama-server instances.
  36. - [llmfit-gui](https://github.com/raiyyan729-cloud/llmfit-gui) — a Windows desktop GUI (PowerShell + WinForms) for llmfit: browse recommendations, download into LM Studio/Ollama, and benchmark, all point-and-click.
  37. ---
  38. ## Documentation
  39. | | |
  40. |---|---|
  41. | **Get started** | [Install](#install) · [Usage](#usage) · [How it works](#how-it-works) |
  42. | **Guides** | [TUI guide](docs/tui.md) · [Benchmarking step-by-step](docs/benchmarking.md) · [CLI & automation](docs/cli.md) · [Cluster mode (Ray / multi-node)](docs/cluster.md) · [Runtime providers](docs/providers.md) · [OpenClaw integration](docs/openclaw.md) |
  43. | **Reference** | [How it works (full)](docs/how-it-works.md) · [Platform & GPU support](docs/platform-support.md) · [Custom models](docs/custom-models.md) · [Development](docs/development.md) |
  44. | **Project** | [Contributing](#contributing) · [Alternatives](#alternatives) · [Code signing](#code-signing) · [License](#license) |
  45. ---
  46. ## Install
  47. ### Windows
  48. #### WinGet
  49. ```sh
  50. winget install --exact --id AlexsJones.llmfit
  51. ```
  52. #### Scoop
  53. ```sh
  54. scoop install llmfit
  55. ```
  56. If Scoop is not installed, follow the [Scoop installation guide](https://scoop.sh/).
  57. ### macOS / Linux
  58. #### Homebrew
  59. Prebuilt binary (recommended, works on all macOS/Linux versions):
  60. ```sh
  61. brew install AlexsJones/llmfit/llmfit
  62. ```
  63. Or from the homebrew-core formula, which builds from source on macOS versions without a bottle:
  64. ```sh
  65. brew install llmfit
  66. ```
  67. #### MacPorts
  68. ```sh
  69. port install llmfit
  70. ```
  71. #### Quick install
  72. ```sh
  73. curl -fsSL https://llmfit.axjns.dev/install.sh | sh
  74. ```
  75. Downloads the latest release binary from GitHub and installs it to `/usr/local/bin` (or `~/.local/bin` if no sudo).
  76. **Install to `~/.local/bin` without sudo:**
  77. ```sh
  78. curl -fsSL https://llmfit.axjns.dev/install.sh | sh -s -- --local
  79. ```
  80. ### uv / pip
  81. To install or update llmfit:
  82. ```sh
  83. uv tool install -U llmfit
  84. ```
  85. To run without installing:
  86. ```sh
  87. uvx llmfit
  88. ```
  89. You can also install llmfit as a Python package in the normal way with tools such as pip or uv.
  90. ### Pre-built Binaries
  91. Download release binaries for Linux, macOS, and Windows directly from the [GitHub Releases](https://github.com/AlexsJones/llmfit/releases) page. Windows binaries are only published once that release's `sign-windows` job has signed, repackaged, and re-checksummed them; if signing is skipped or fails, the Windows assets are held back and attached by a re-run of the release workflow (with its fresh signing requests approved) rather than shipped unsigned. Releases before v1.1.19 did not have this guard, so verify the executable signature on older versions if you require a signed binary.
  92. ---
  93. ## Container Deployment
  94. `llmfit` provides a multi-architecture Docker image (`ghcr.io/alexsjones/llmfit`) supporting both interactive CLI/TUI and headless Web UI / API server modes.
  95. ### Interactive TUI
  96. To launch the interactive TUI instead, pass the global `--tui` flag:
  97. ```sh
  98. docker run -it --rm ghcr.io/alexsjones/llmfit --tui
  99. ```
  100. ### Non-Interactive
  101. This prints JSON from `llmfit recommend` command.
  102. ```sh
  103. docker run ghcr.io/alexsjones/llmfit
  104. ```
  105. This prints JSON from `llmfit recommend` command. The JSON could be further queried with `jq`.
  106. ```
  107. podman run ghcr.io/alexsjones/llmfit recommend --use-case coding | jq '.models[].name'
  108. ```
  109. To launch the interactive TUI instead, pass the global `--tui` flag:
  110. ```sh
  111. docker run --rm -it ghcr.io/alexsjones/llmfit --tui
  112. ```
  113. ### From source
  114. ```sh
  115. git clone https://github.com/AlexsJones/llmfit.git
  116. cd llmfit
  117. cargo build --release
  118. # binary is at target/release/llmfit
  119. ```
  120. ---
  121. ## Usage
  122. ### Terminal Interface (TUI)
  123. Launch `llmfit` in your terminal without flags to start the interactive browser:
  124. ```sh
  125. llmfit # interactive TUI: your hardware, every model, ranked
  126. ```
  127. The TUI shows your detected specs at the top and every model scored for fit, speed, quality, and context. See the [TUI guide](docs/tui.md) for navigation, planning, simulation, downloads, the community leaderboard, and benchmarking.
  128. Keybindings inside the TUI:
  129. - `b`: Open community benchmarks; `I`: Open live inference benchmarks
  130. - `h`: Show help and keybindings
  131. - `↑` / `↓` or `k` / `j`: Navigate list items
  132. - `/`: Filter models by name, family, or quantization
  133. - `Esc`: Clear search / Back
  134. ### Command Line Options
  135. ```sh
  136. # Print hardware telemetry and recommended models to standard output
  137. llmfit recommend
  138. # Output system profile and recommendations in raw JSON format
  139. llmfit recommend --json
  140. # Estimate SSD capacity for keeping three runnable models
  141. llmfit storage --keep 3 --selection largest --json
  142. # Start the native HTTP API server
  143. llmfit serve --host 0.0.0.0 --port 8787
  144. ```
  145. See [model library storage](docs/cli.md#model-library-storage) for selection,
  146. OS reserve, download scratch, free-space headroom, and hardware simulation.
  147. ### Web UI & API Server
  148. ```sh
  149. docker run -d -p 8787:8787 ghcr.io/alexsjones/llmfit serve
  150. ```
  151. #### Docker Compose
  152. ```yaml
  153. ---
  154. services:
  155. llmfit:
  156. image: ghcr.io/alexsjones/llmfit:latest
  157. container_name: llmfit
  158. restart: unless-stopped
  159. command: ["serve", "--host", "0.0.0.0", "--port", "8787"]
  160. ports:
  161. - "8787:8787"
  162. healthcheck:
  163. test: ["CMD", "curl", "-f", "http://localhost:8787/health"]
  164. interval: 15s
  165. timeout: 5s
  166. retries: 3
  167. start_period: 10s
  168. ```
  169. For scripts, agents, and classic terminal output:
  170. ```sh
  171. llmfit fit # table of all models ranked by fit
  172. llmfit fit --show-incompatible # also show backend-incompatible models as non-runnable
  173. llmfit recommend --json # top picks as JSON (agent/script consumption)
  174. llmfit info "<model>" # one model: fit analysis, estimate basis, verify commands
  175. llmfit bench # measure real tok/s/TTFT against your running provider
  176. llmfit doctor # hardware detection report for bug reports
  177. llmfit serve # start the api and web user interface
  178. ```
  179. Full reference: [CLI & automation](docs/cli.md).
  180. ### Cluster mode (Ray / multi-node)
  181. > **Preview:** so far tested only against a mock Ray Dashboard. If you run Ray, please share the output of `curl <dashboard>/nodes?view=summary` in an [issue](https://github.com/AlexsJones/llmfit/issues/new).
  182. Check which models fit across several machines, such as 3 × DGX Spark or a couple of multi-GPU servers running Ray and vLLM:
  183. - **Know before you launch:** find out whether a model fits across your machines before you spend an hour starting vLLM.
  184. - **Catch splits vLLM would refuse:** most models can't be split 3 ways across 3 GPUs. llmfit picks a split vLLM accepts, or says none fits, instead of letting vLLM crash at startup.
  185. - **One reviewable file:** Ray discovery writes a single `cluster.toml`, so you don't have to tally VRAM by hand.
  186. - **Changes nothing:** llmfit reads Ray's dashboard once and never launches or schedules anything.
  187. ```sh
  188. llmfit cluster init --ray-url http://<head>:8265 # or hand-write cluster.toml
  189. llmfit cluster status
  190. llmfit --cluster fit
  191. ```
  192. See the [cluster guide](docs/cluster.md) for walkthroughs, Ray token handling and today's limits.
  193. ---
  194. ## Community & Benchmarks
  195. `llmfit` includes hardware detection and performance benchmarks contributed by the community. You can share your hardware benchmark results using:
  196. ```sh
  197. llmfit bench --share
  198. ```
  199. ---
  200. ## How it works
  201. llmfit detects your hardware (RAM, CPU, GPU/VRAM, backend), then scores every model in its catalog across four dimensions: memory fit, estimated speed, quality, and context. Speed estimates come from a memory-bandwidth model grounded in runtime sampling and real community measurements — and every estimate ships its inputs, so `llmfit info` shows exactly what a number assumes and how to verify it on your machine.
  202. Full detail, including the estimation formulas and the model database: [How llmfit works](docs/how-it-works.md).
  203. ---
  204. ## Contributing
  205. Contributions are welcome, especially new models.
  206. ### Before submitting a PR
  207. Please run `cargo fmt` before pushing your changes. Most CI check failures are caused by unformatted code:
  208. ```sh
  209. cargo fmt
  210. ```
  211. Guides for adding models — locally (no rebuild) or to the built-in catalog: [Custom models](docs/custom-models.md).
  212. ---
  213. ## Alternatives
  214. If you're looking for a different approach, check out [llm-checker](https://github.com/Pavelevich/llm-checker) -- a Node.js CLI tool with Ollama integration that can pull and benchmark models directly. It takes a more hands-on approach by actually running models on your hardware via Ollama, rather than estimating from specs. Good if you already have Ollama installed and want to test real-world performance. Note that it doesn't support MoE (Mixture-of-Experts) architectures -- all models are treated as dense, so memory estimates for models like Mixtral or DeepSeek-V3 will reflect total parameter count rather than the smaller active subset.
  215. ---
  216. ## Code signing
  217. llmfit's Windows release binaries are intended to be digitally signed (Authenticode) via [SignPath.io](https://about.signpath.io/), with a free code signing certificate provided by the [SignPath Foundation](https://signpath.org/). The release workflow only attaches Windows assets after the `sign-windows` job has signed, repackaged, and re-checksummed them; when signing is skipped or fails, the Windows zips (and the PyPI Windows wheels built from them) are held back until the workflow is re-run against the tag and the new signing requests that re-run submits are approved. Releases before v1.1.19 could publish an unsigned Windows artifact, so verify the executable signature on those before relying on it.
  218. Signing happens automatically in the [release pipeline](.github/workflows/release.yml): only artifacts built by GitHub Actions from this repository are submitted for signing, and signing requests are approved by the project maintainer ([@AlexsJones](https://github.com/AlexsJones)).
  219. **Code signing policy:** see the [SignPath Foundation code signing policy and terms](https://signpath.org/terms).
  220. **Privacy:** this program will not transfer any information to other networked systems unless specifically requested by the user or the person installing or operating it. llmfit only contacts external services when you explicitly use the corresponding feature (e.g. model downloads, runtime provider queries, or the community leaderboard).
  221. ---
  222. ## License
  223. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.