Open source · Apache-2.0 · Runs on your computer

Open models, fitted to your rig.

Rigbrew scans your computer, shows which open AI models can actually run on it, and runs a build that was measured for that class of hardware. Chat and pictures share one conversation today; video and voice download now and join it next. No usage limits, and nothing you type goes to a model provider.

macOS beta comingWindows next, Linux later

Download status and requirements
0:00/ 0:27
Recorded from the app on a MacBook Pro M5 Max, 1440 × 900, once in each appearance. The picture took about 52 seconds; that stretch plays ten times faster here. Nothing else is cut.

01 Will it fit

Pick a machine. Watch what fits.

Rigbrew never hands a model all of the memory. It keeps room for the system and your other programs, then seats each model in what is left, and picks the lightest version that still clears its quality bar.

10.7GB

may hold a model, of 16 GB unified memory, shared by the processor and the GPU.

5.3 GB stays with the system and your other programs.

Class Apple Silicon, up to 16 GB

  1. Steep 4B Chat Balanced · q5
    Fits on the GPU

  2. Crema 6B Pictures Balanced · int8
    Fits on the GPU

  3. Pour 5B Video smallest version: q4
    Too big 0.6 GB short

    Download only for now: running it in Rigbrew comes later.

  4. Whistle 82M Voice Standard · f32
    Fits on the processor

    Download only for now: running it in Rigbrew comes later.

Chat and pictures run here today. Video needs 0.6 GB more than this machine can give.

Memory figures are the manifest’s estimates. The rules are core/src/hardware/tier.rs and core/src/select.rs, run here in your browser. One model is in memory at a time, so each is measured against the whole budget.

02 One chat, every model

Ask for a picture in the middle of a conversation.

Each family installs on its own and the chat uses whatever is installed. Ask Steep for a picture and it calls Crema; switch the box to Picture and you go straight there. Video and voice download today and join the chat later.

  1. You ask, in plain words.

    “Draw a paper boat on a pond, then say one sentence about it.”

  2. Steep asks for a picture.

    The chat model calls generate_image by itself. No mode to switch, no second app.

  3. Crema draws it, here.

    1024 × 1024, 8 steps, 50.5 s on the GPU of a MacBook Pro M5 Max.

  4. Steep finishes the turn.

    13 tokens at 113.3 tokens per second, measured by the app in this chat.

  5. One model in memory at a time.

    The bay along the bottom shows what is loaded. Rigbrew swaps models as the chat needs them.

Rigbrew, Pro level: a chat titled Paper boat. The message asks for a paper boat on a pond; a tool line reads generate_image, Crema 6B, int8, 1024 by 1024, 8 steps, 50.5 seconds; the picture of a white paper boat among reeds; then Steep 4B answers in one sentence at 113.3 tokens per second. Rigbrew, Pro level: a chat titled Paper boat. The message asks for a paper boat on a pond; a tool line reads generate_image, Crema 6B, int8, 1024 by 1024, 8 steps, 50.5 seconds; the picture of a white paper boat among reeds; then Steep 4B answers in one sentence at 113.3 tokens per second.
The app, unedited: a chat from the developer’s MacBook Pro. Pictures, audio and video never leave the computer.

03 Measured, not promised

Every build is checked against the original.

Before a build ships it is compared with the full-precision model it came from. The dashed line is the bar; Rigbrew takes the lightest build above it, not the biggest one that fits.

96.4%

Steep 4B Balanced picks the same next token as the full-precision original, at 3.2 GB on disk instead of 8.7 GB.

87.8%

Crema 6B Balanced, our own int8 conversion: by eye, its pictures cannot be told from the original’s. 6.2 GB instead of 12.3 GB.

12

builds in the catalogue, each listed with what it was measured against, and what was not measured yet.

Steep 4B: five builds Same next token as the original
85%90%95%100%3456 GBmemory it needsRIGBREW'S BAR · 96%q3q4q5q6q8

wikitext-2 test set, 32 × 512 tokens, against the full-precision original. The importance matrix halves the error of q4: KL 0.0374 without it, 0.0202 with it.

Crema 6B: four builds Picture similarity to the original (1 − LPIPS)
60%70%80%90%78910 GBmemory it needsRIGBREW'S BAR · 85%q4q5int8q8

6 prompts at 1024 × 1024, 8 steps, fixed seed, against the full-precision original. The smaller two lose fine texture; the smallest also shifts the composition, though its pictures are still usable.

Whistle 82M: smaller was worse

We tried shrinking it. On the processor, the smaller builds were slower and made more mistakes, so it ships at full precision.

BuildSizeWord errorsTime per second of speech
Full precision (ships)326 MB6.2%0.75 s
int8, matrix layers279 MB6.9%0.97 s
int8, everything114 MB8.5%2.96 s

10 sentences, one voice, on the processor; word error rate after transcribing the audio back to text, one processor thread.

Pour 5B: not measured yet

Both builds ran and the motion looked coherent. Quality against the original has not been measured yet. Until it is, the catalogue says n/m instead of a number.

Test: 33 frames at 480 × 832, 20 steps.

About the speeds

The lab machine was busy with other builds during these runs, so lab timings only compare builds with each other. In the chat above, on the same MacBook Pro, Steep ran at 113.3 tokens per second.

Every build, every number
BuildVersionMemoryDownloadQualityMeasured as
Steep 4B q3Smallest3.3 GB2.5 GB86.9%same next token; KL 0.0819; 62.5 tok/s
Steep 4B q4Small3.7 GB3 GB93.2%same next token; KL 0.0202; 66.3 tok/s
Steep 4B q5Balanced4.1 GB3.3 GB96.4%same next token; KL 0.0066; 54.6 tok/s
Steep 4B q6Better4.4 GB3.7 GB97.3%same next token; KL 0.0026; 50.4 tok/s
Steep 4B q8Best quality5.4 GB4.6 GB99.1%same next token; KL 0.0005; 52.4 tok/s
Crema 6B q4Smallest7.2 GB5.7 GB66.7%1 − LPIPS; SSIM 0.710; PSNR 16.3 dB
Crema 6B q5Small7.9 GB6.4 GB77.0%1 − LPIPS; SSIM 0.770; PSNR 18.9 dB
Crema 6B int8Balanced9.7 GB8.3 GB87.8%1 − LPIPS; SSIM 0.858; PSNR 22.8 dB
Crema 6B q8Best quality10 GB8.6 GB88.3%1 − LPIPS; SSIM 0.861; PSNR 22.8 dB
Pour 5B q4Smaller11.3 GB8.3 GBn/mnot measured: 33 frames, 480x832, 20 steps: ran and looked coherent
Pour 5B q8Better quality16.2 GB13.3 GBn/mnot measured: 33 frames, 480x832, 20 steps: ran and looked coherent
Whistle 82M f32Standard700 MB384 MB100.0%weights unchanged; word errors 6.2%

From the package manifest; how each kind of model is measured is in docs/models.md. Memory figures are estimates.

Each of these runs costs hours on a fast machine. Sponsors pay for the measurements, and every result is published, including the ones that did not work out.

04 Families

Five families. One name each.

Rigbrew converts and measures open-weight models in its own lab, then ships them under its own names. Only models under Apache-2.0, MIT or CC-BY-4.0 are packaged, and every package carries its licence and notice files.

  1. 01

    Steep

    Chat

    Answers questions, writes and explains. The model you talk to. It can call the other installed families for you.

    Steep 4B ·5 builds ·3.3–5.4 GB ·Apache-2.0

    Runs today
  2. 02

    Crema

    Pictures

    Makes a picture from a description. Adds Picture mode to the chat, and Steep can ask it for a picture when you want one.

    Crema 6B ·4 builds ·7.2–10 GB ·Apache-2.0

    Runs today
  3. 03

    Pour

    Video

    Makes short video clips from a description. Downloads today. Running it inside Rigbrew comes later.

    Pour 5B ·2 builds ·11.3–16.2 GB ·Apache-2.0

    Download now, runs later
  4. 04

    Whistle

    Voice

    Reads text aloud. Downloads today. Reading answers aloud in the chat comes later.

    Whistle 82M ·1 build ·700 MB ·Apache-2.0

    Download now, runs later
  5. 05

    Sift

    Listening

    Turns speech into text. Planned: dictate instead of typing.

    No package yet

    Planned

Modules are drawn to scale: the memory of the version Rigbrew picks on a 48 GB Mac, on a ruler that ends at 18 GB.

Every build, with its numbers

05 Start simple, grow pro

Plain words first. Every number when you want it.

A new install starts at Guided: names by what they do, one button per model. One setting shows more, up to every build with its measurements. Below, the same Models screen at each level.

  • Names by what they do: “Chat (Steep 4B)”
  • Only the version Rigbrew picked for this machine
  • “Fast on this Mac” instead of tokens per second
  • A tour, a checklist and tips

One setting changes every screen. The app may suggest the next level once you use it more; it never switches by itself, and switching installs or removes nothing.

Models in Guided: four rows, Chat, Pictures, Voice and Video, each with one action. Models in Guided: four rows, Chat, Pictures, Voice and Video, each with one action.

06 Privacy and open source

Runs here. Says what it sends.

The models run on your computer and keep working offline. The app does report to Rigbrew’s own server, in two layers, and lists everything it has queued to send.

What you type is never sent to a model provider.

Always Basic usage
What was opened, installed and loaded, how fast it ran, errors, the hardware class, the app version and a random install ID. Never what you type or what the models answer. Not linked to an account, and the IP address is not stored.
With consent Content
The text of prompts and answers, linked to an account so it can be exported or deleted. The app asks for this at first start and does not run without it; withdraw it in Settings and whatever has not been sent is deleted. Builds from source have no account module and never send content.
  • Pictures, audio and video you make are never uploaded.
  • Settings › Privacy and data lists every event before it is sent.
  • Developers switch basic usage off with DO_NOT_TRACK=1.
  • This site counts page views without cookies and stores nothing on your device.

Read the Privacy Policy (a draft, not yet reviewed by a lawyer)

Apache-2.0. Read every line that runs.

rigbrew/
├─ core/       Rust: scan, selector, downloader, engines
├─ daemon/     rigbrewd, the local service
├─ cli/        rigbrew on the command line
├─ app/        the desktop app, Tauri 2 and SvelteKit
└─ docs/       architecture, the local API, models

The ruler at the top of this page runs the same budget rules as tier.rs, and the code that sends usage data is in events.rs and cloud.rs.

07 In the open

Built in the open. Counted in the open.

These numbers come live from Rigbrew’s server, as they are, starting from zero. Sponsors pay for the machine hours behind every build and every measurement.

Live from Rigbrew’s server

GitHub stars
–
Contributors
–
Installs
–
Downloads
–
Sponsors
–

Counted from the first day, not rounded up. A zero shows as new.

08 Get started

Not downloadable yet. Getting close.

macOS on Apple Silicon comes first. Until the beta is signed and published, Rigbrew runs from source, and the steps are short.

  1. macOS Apple Silicon Beta coming Runs from source today. A signed download is next.
  2. Windows Graphics card or not Next After macOS. The budget rules above already cover graphics cards.
  3. Linux Later Planned after Windows.

To hear when the beta is out, watch the repository’s releases on GitHub. There is no mailing list.