Skip to main content

Mind LabLanguage modelWeights available

Macaron-V1-Coding-Venti

PopularityRank 289 of 339 language models

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.

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.

All specifications

Architecture

Checkpoint
mindlab-research/Macaron-V1-Coding-Venti
Source: Checkpoint
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

Input
Text
Source: Input
Output
Text
Source: 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

Mint API model ID
macaron-v1-coding-venti
Source: Mint API model ID

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

Context windowTokens the model reads at once · higher is better
Macaron-V1-Coding-VentiRank 12 of 1121.05M
Gemini 4 Carbon1.05M
Gemini 4 Argon1.05M
Muse Wonder1.05M
Kimi K3.1 Pro1.05M
Muse Ember 1.01.05M
Gemini 3.7 Flash1.05M

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

Sources and data date

Show all 11 sources
TypeEvidence and data date
Input

Documented modalities. Retrieved November 16, 2026.

Output

Documented modalities. Retrieved November 16, 2026.

Additional sourceMind Lab Macaron-V1 family announcement (retrieved November 16, 2026) · Mind Lab Macaron-V1 release announcement · Editorial description reviewed November 16, 2026
Additional sourceMacaron-V1-Coding-Venti checkpoint configuration (retrieved November 16, 2026)
Additional sourceMint Recursive hosted model IDs (retrieved November 16, 2026) · Mint Recursive hosted model IDs · Editorial description reviewed November 16, 2026
Additional sourceMind Lab Macaron-V1 Hugging Face collection (retrieved November 16, 2026)
Additional sourceOpenRouter: Popularity index (derived), CC BY 4.0
Additional sourceVercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional sourceOllama: cumulative downloads for the popularity index
Additional sourceReplicate: cumulative runs for the popularity index
Additional sourceGoogle Trending Now: limited feed selection for Germany and the US
Additional sourceCreative Commons Attribution 4.0