Our pledge

10% of revenue, from the first dollar.

Of every dollar RigSpark earns, 10 cents goes to education and AI access. It comes off revenue, not profit, so it is paid in loss-making months too.

10%of revenue, not profit
Educationand access to AI
Day onefrom the first dollar earned
Read the full pledge
New RigSpark 3.1.0 · What’s new

AI has no taste. You do.

Sparky checks your RAM, GPU and disk, picks the best model that fits, then downloads, verifies and runs it: chat, images, short video and voice. All on your machine.

  • Best fit for your hardware
  • Text, image, video, voice
  • yes / slow / no, with speed
  • Free, open source, offline
Download for macOSCommunity Edition Other platforms

Community Edition · Free and open source · Apple Silicon · macOS 12 or later

rigspark/rigsparkStar

Your best fit, picked by Sparky

Pick your Mac’s memory and what you want to run.

Best fit

gpt-oss:20byes

Best.

    rigspark up gpt-oss:20b

    Then rigspark chat. How Sparky ranks every model ›

    266
    models in the catalog, plus any GGUF from Hugging Face
    5
    runtimes: Ollama, llama.cpp, MLX, LM Studio, BitNet
    MIT
    free and open source

    Not just a checker

    Pick it, then run it.
    Every kind of local AI.

    One app. Sparky picks the model, you use it.

    How it works

    Sparky picks the best model your machine can hold, downloads it, checks its SHA-256 and starts it on 127.0.0.1. You chat, generate or talk in the same app.

    What each one needs

    Text is ranked across the whole catalog. Images and video run through your own ComfyUI. Spoken replies need Apple silicon; PCs attach a local speech server.

    Three moods. One honest answer.

    Yes. Slow. No.
    Before you download.

    This is how Sparky picks. Every model in the catalog gets a verdict sized to your machine, with the reason it was given.

    Three Sparky robots: a smiling amber visor, a sleepy yellow visor and a red visor with crossed-out eyes

    How it works

    One command ranks
    every model.

    rigspark recommend sizes each model’s weights and KV cache against your machine and ranks the offline catalog. Models that can’t fit are listed with the reason.

    $ rigspark recommend
Ranked local LLMs for arm64/darwin (34.0 GiB ram usable):

Rank  Model              Params  Est. Mem  Verdict   Est. tok/s
   1  qwen3:30b-a3b         30B  19.9 GiB  ✓ yes    55.6–103.3
   2  kimi-vl-a3b           16B  10.7 GiB  ✓ yes    55.6–103.3
   3  qwen3:32b             32B  21.6 GiB  ⚠ slow      5.2–9.7
   4  deepseek-r1:32b       32B  21.3 GiB  ⚠ slow      5.2–9.7
   5  gemma3:27b            27B  18.6 GiB  ⚠ slow     6.2–11.5
   ⋮

Run the top pick:  rigspark up qwen3:30b-a3b

Won't fit (14):
  ❌ deepseek-r1:671b  (ram-bound)
  ❌ llama3.3:70b      (ram-bound)
    Real output on an arm64 Mac with 34.0 GiB of usable RAM (quant, backend and license columns trimmed).
    1. Score. Hardware is detected locally. Unknown figures stay unknown; nothing is invented.
    2. Check. rigspark can-run qwen3:8b gives one verdict and exits non-zero only on no, so it works as a CI gate.
    3. Run. rigspark up pulls, verifies the weights and serves on 127.0.0.1. Then rigspark chat.
    Real rigspark recommend output and the browser workspace. Unmute for sound.
    New in 3.0.5

    A real Mac app

    Install, click once, chat. llama.cpp built in.

    Download for Mac
    Sparky waving hello
    New in 3.0.3

    Ming Design UI/UX mockups

    UI/UX mockups with Ming Design, plus FLUX.1 schnell and Wan 2.1.

    Limits

    Runs through your own ComfyUI. Ming Design INT8 is tested on a 36 GiB Apple Silicon Mac; CUDA is unverified. Text inside generated images may be garbled.

    Read the changelog
    Real Ming Design generation in RigSpark chat: a plant-care mobile app mockup rendered inline through local ComfyUI

    Privacy

    Your hardware.
    Your data. Your call.

    Most “can I run it” tools guess. Sparky refuses to. Every figure is sourced, or it says unknown.

    Sparky standing in a studio spotlight

    • Offline advice.

      recommend, can-run and doctor make zero network calls. Same catalog, same answer.

    • Unknown stays unknown.

      Unsourced throughput is printed as unknown. Models are still ranked by weights, never dropped.

    • Fail-closed integrity.

      up and switch check pulled weights against the catalog digest and refuse anything that doesn’t match.

    • Loopback only.

      Model servers and the workspace bind to 127.0.0.1 with host-header checks.

    Which is right for you?

    Ollama is an excellent runtime. RigSpark sits on top of it and four others, picks what to run, then runs it.

    A runtime alone

    Ollama, llama.cpp, MLX or LM Studio

    • Run inference
    • Not included: Hardware-aware recommendations
    • Not included: yes / slow / no verdicts + est. tok/s
    • Not included: AI Hardware Score (0–100)
    • Not included: KV-cache-aware context sizing
    • Not included: Loopback-only browser workspace
    • Not included: Agents, skills & MCP tools
    • Not included: Multi-backend (5 runtimes)
    • Not included: SHA-256 integrity verification
    • Not included: Portable memory migration
    • Not included: Offline, deterministic advice

    Runtime + RigSpark

    Sparky decides, your runtime runs

    • Run inference
    • Hardware-aware recommendations
    • yes / slow / no verdicts + est. tok/s
    • AI Hardware Score (0–100)
    • KV-cache-aware context sizing
    • Loopback-only browser workspace
    • Agents, skills & MCP tools
    • Multi-backend (5 runtimes)
    • SHA-256 integrity verification
    • Portable memory migration
    • Offline, deterministic advice

    Community Edition · Available now

    Get RigSpark.

    RigSpark Community Edition is free, open source and available now for macOS and Windows. The desktop app bundles llama.cpp, so the first model runs right after install. No Node.js, Python or compiler needed.

    The Mac app is signed with a Developer ID and notarized by Apple, so it opens like any other app.

    If Windows SmartScreen warns about the installer: More info → Run anyway. Signed Windows builds are on the way (code signing policy).

    More downloadsCommand line for macOS, Linux and Windows, Homebrew, cargo and Docker

    Command line

    Homebrewbrew install shashankswe2020-ux/tap/rigspark
    cargo-binstallcargo binstall rigspark-cli rigspark-gui
    From sourcecargo install rigspark-cli --locked --bin llmup --bin rigspark && cargo install rigspark-gui --locked
    Containerdocker pull ghcr.io/rigspark/rigspark:latest

    Archives are unsigned. Verify them against SHA256SUMS. On macOS, clear quarantine with xattr -dr com.apple.quarantine rigspark-*. The container is an older CLI image that sees only the container’s resources.

    Questions? Sparky has answers.

    Figures are RigSpark’s offline estimates, not benchmarks.

    How do I find out which LLMs my computer can run?

    Install RigSpark and run rigspark recommend. It detects your GPU, VRAM, RAM and free disk, ranks every catalog model with a yes, slow or no verdict and estimated tokens per second, and lists the models that won’t fit with the reason. rigspark can-run <model> checks a single model.

    How much VRAM do I need to run an 8B, 14B, 32B or 70B model?

    At Q4_K_M and default context, RigSpark estimates about 5.3 GiB for Llama 3.1 8B, 9.9 GiB for Qwen3 14B, 21.6 GiB for Qwen3 32B and 45.5 GiB for Llama 3.3 70B. Longer contexts add KV cache on top.

    Can I run local LLMs on a Mac with Apple Silicon?

    Yes. Apple Silicon GPUs share unified memory with the CPU, so RigSpark sizes models against system memory and auto-selects MLX for models with an MLX build, then Ollama, then llama.cpp.

    Can RigSpark generate images and videos locally?

    Yes. With your own ComfyUI running on 127.0.0.1, rigspark generate image or rigspark generate video installs pinned, SHA-256 verified FLUX.1 schnell or Wan 2.1 weights and runs a built-in workflow. You can also switch the chat composer to Image or Video in rigspark gui. Paid ComfyUI Partner nodes are refused and nothing is sent to the cloud.

    Does RigSpark send my data anywhere?

    Recommendations, can-run and doctor make no network calls and use a verified local catalog. The explicit catalog --update action downloads a signed snapshot; normal startup does not. Model servers and the browser workspace bind to 127.0.0.1 only.

    Is RigSpark the same project as llmup?

    Yes. RigSpark 2.0 renamed llmup. The llmup command remains as a compatibility alias, and the crates moved from llmup-* to rigspark-*. See the changelog for moving your data directory.

    RigSpark

    Let Sparky check your rig.

    Free and open source. MIT licensed. Native Rust.

    DownloadStar on GitHub
    Sparky with arms out, ta-da