Aug 5, 2026 · you are here
MacawNot publicly ranked · Price not listed
Model profile · Bad Theory Labs
Macaw
Released Aug 5, 2026 — see all recent releases
Macaw is tracked, but not publicly ranked yet. The profile exposes 0 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Data as of August 11, 2026 · How the score is built
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not publishedBad Theory Labs Macaw model card
- Context window
- 128KBad Theory Labs Macaw model card
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Local Apple Silicon macOS assistant with 97 macOS tools; the 4-bit MLX checkpoint is documented at roughly 1.5 GB on disk.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordBad Theory Labs Macaw model card
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersLineage
The sequence follows explicit supersedes links. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
v1 · v1
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Macaw, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
Macaw is a open weight model with a 128K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Local Apple Silicon macOS assistant with 97 macOS tools; the 4-bit MLX checkpoint is documented at roughly 1.5 GB on disk.
Official launch snapshot from Bad Theory Labs' Macaw page and matching MLX model card. Macaw is a local macOS tool-use model derived from LFM2.5-2.6B, with a 128K context window and LFM Open License v1.0 weights. The provider's 10-request tool-call suite is a product-specific check, not a comparable public benchmark, so BenchLM records no ranking benchmark values for this model.
The profile has no source-displayable benchmark row yet.
Radar
Full release historyMacaw release history
Macaw released
Bad Theory Labs · Model release
Source confirmed
Frequently asked questions
How does Macaw perform overall in AI benchmarks?
Macaw does not have any source-displayable benchmark rows yet, so this profile does not assign a public score or rank. Documented specifications remain visible, while score-led charts and claims stay unavailable until a published evaluation can be attached to the exact model.
Is Macaw open source?
Macaw is an open-weight model from Bad Theory Labs. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does Macaw have full benchmark coverage on BenchLM?
No. Macaw currently has 0 source-displayable rows across 381 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Macaw?
Macaw has a documented context window of 128K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.
Last updated August 11, 2026. Runtime fields remain blank until a sourced snapshot exists.
Watch Macaw in the weekly brief
Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.
Read a sample issueJoin 2,000+ readers.