Mind LabLanguage modelWeights available
Macaron-V1-Coding-Venti
21out of 100first value
usage data only, range 8 to 35
Summary
Macaron-V1-Coding-Venti is a separate merged GLM-5.2 checkpoint derived from Macaron-V1-Venti's coding specialist. It targets software engineering, terminal, and repository tasks.
The checkpoint needs no runtime routing and does not include the routed Venti model's Chat, Agent, or Generative UI specialists. A separate evaluation of this checkpoint has not been published.
On this page
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
The 100 most popular models of this category, 0 to 100, higher is more popular
20 of 101 models
As of November 2026 · Source: gradually.ai popularity index
Over time
First value from November 16, 2026. The timeline appears from the second week.
What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.
Similar models
More models of the same kind as Macaron-V1-Coding-Venti, chosen by model line, developer, size, price and release date.
All specifications
Architecture
- Base model
- GLM-5.2. The merged checkpoint retains the 744B base footprint, according to the model card.
- Source: Base model
- Model class
- Coding model for software engineering, terminal, and repository tasks. A standalone evaluation of this merged checkpoint has not been published.
- Source: Model class
Input and output
- Context window
- 1,048,576 positions in the checkpoint configuration; the model card states 1 million tokens.
- Source: Context window
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
- Weights license
- MIT license according to the model card. Any applicable base-model and dependency requirements must also be observed.
- Source: Weights license
- Shutdown
- None announced
- no source
API
Further details
- Relationship to Venti
- Separate merged checkpoint: Mind Lab merges Macaron-V1-Venti's L2 Coding LoRA directly into the GLM-5.2 base. It has no runtime router and no Chat, Agent, or GenUI specialists.
- Source: Relationship to Venti
- Release date
- The V1 announcement dated July 21, 2026 lists the merged coding checkpoint. It does not show whether that entry was added later, so a separate public release date remains unconfirmed.
- Source: Release date
Frequently asked questions about Macaron-V1-Coding-Venti
How large is the context window of Macaron-V1-Coding-Venti?
1.05 M tokens. That is how much text Macaron-V1-Coding-Venti reads at once, about 1,570 A4 pages.
Page count as a rule of thumb from Artificial Analysis
Can I run Macaron-V1-Coding-Venti locally?
Yes, the weights are open. With 744B parameters it needs a lot of memory, more a server than a laptop.
Stated by Mind Lab
- Open weights
- yes
- License
- MIT license according to the model card. Any applicable base-model and dependency requirements must also be observed.
- Parameters
- 744B
- active per token
- n/a