mindlab-research

Macaron-V1-Venti

Highlights

A 748B-parameter flagship model, consisting of a 744B GLM-5.2 base model and four 1B-parameter LoRA specialists across Chat, Agent, Coding, and GenUI.
The first model to be post-trained on GLM-5.2, moving Macaron's personal-intelligence stack beyond Macaron-V1-Preview.
Model-and-harness co-design: post-trained with MinT and MindForge for production-aligned routing, tool use, UI4A Generative UI, and agent workflows.
Long-context post-training infrastructure: the V1 training stack incorporates LongStraw for multi-million-token RL execution, with Venti supporting a 1M context length.
Broad evaluation across personal intelligence, agentic tasks, coding, terminal use, and Generative UI; Macaron V1 leads the listed baselines on ChatBench, LivingBench, PinchBench, TerminalBench 2.1, and UI4ABench.

Model Overview

Table with columns: Field, Value
Field	Value
Model name	Macaron-V1-Venti
Organization	MindLab Research
Release family	Macaron-V1
Base model	GLM-5.2
Architecture	GLM-5.2 base + Mixture of LoRA (MoL) specialists
Parameter footprint	748B total: 744B base + 4 x 1B LoRA specialist parameters
Specialists	L0 Chat, L1 Agent, L2 Coding, L3 GenUI (1B each)
Post-training system	MinT + MindForge
Primary domains	Personal intelligence, tool use, coding, Generative UI
Context length	1M
Precision / serving format	BF16 base checkpoint with routed LoRA serving
License	MIT

Mixture of LoRA (MoL) Architecture

Table with columns: Adapter, Role, Description
Adapter	Role	Description
`l0`	Chat	Conversational and instruction-following backbone; entry point for routing.
`l1`	Agent	Personal-life agent tasks, heavy tool use, long-horizon planning, and dynamic workflows.
`l2`	Coding	Code understanding, SWE tasks, terminal use, and repository workflows.
`l3`	GenUI	UI4A rendering and UI-driven action.

At runtime, L0 routes each new user request to the most suitable specialist. Ongoing reasoning and tool interactions remain within the selected LoRA, while completed work can be shared across specialists through concise summaries.

Evaluation

Macaron-V1 benchmark results

Table with columns: Benchmark, Macaron V1, GLM 5.2, GPT 5.5, Claude Opus 4.8, Gemini 3.1 Pro, Qwen 3.7 Max, Minimax M3
Benchmark	Macaron V1	GLM 5.2	GPT 5.5	Claude Opus 4.8	Gemini 3.1 Pro	Qwen 3.7 Max	Minimax M3
ChatBench	58.3	54.5	55.5	52.8	52.0	52.5	49.1
LivingBench	64.0	60.5	61.9

Higher is better for all scores shown in the chart and table.

Evaluation Protocols

The headline table reports aggregate scores from the Macaron-V1 evaluation suite covering personal intelligence, agentic tool use, coding, terminal workflows, and Generative UI.

Hugging Face ingestible result files are included under .eval_results for SWE-bench Verified. The full model-card table is also mirrored in evaluation/benchmark_summary.yaml for reproducibility and downstream parsing.

The full benchmark methodology will be released with the technical report.

Usage

Hosted API

The hosted API is available at https://mintcn.macaron.xin/. Use the site for current model names, authentication, pricing, and rate-limit details.

For OpenAI-compatible deployments, requests follow the standard chat-completions shape:

bash
curl https://mintcn.macaron.xin/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <api-key>" \
  -d '{
    "model": "Macaron-V1-Venti",
    "messages": [
      {"role": "user", "content": "Create a compact dashboard UI for tracking weekly fitness goals."}
    ],
    "temperature": 0.2,
    "max_tokens": 2048
  }'

Mixture of LoRA (MoL) Serving

For self-hosted routed serving, use the Mixture of LoRA (MoL) serving harness. The harness keeps the endpoint OpenAI-compatible while adding an L0 router, server-side LoRA metadata, and same-request switching into the selected specialist.

See the MoL serving repository for more details.

Macaron Artifacts

Macaron Artifacts is the companion local WebUI and plugin bundle for viewing Macaron sessions and GenUI output. It supports Claude Code, Codex, and Kimi Code, and can run against Macaron or another Anthropic-compatible endpoint.

Install it as a plugin in the agent runtime you use:

text
# Claude Code
/plugin marketplace add https://github.com/MindLab-Research/macaron-artifacts
/plugin install macaron@macaron

bash
# Codex
codex plugin marketplace add https://github.com/MindLab-Research/macaron-artifacts
codex plugin add macaron@macaron

text
# Kimi Code
/plugins install https://github.com/MindLab-Research/macaron-artifacts
/reload

The WebUI can be configured from its settings page, or through environment variables:

bash
MACARON_API_BASE=https://mintcn.macaron.xin/v1
MACARON_API_KEY=<api-key>
MACARON_MODEL=Macaron-V1-Venti

The plugin includes the genui-builder skill so supported agents can produce GenUI TSX and preview the rendered artifact in the browser. See the Artifacts repository for full install, update, and provider configuration details.

License

This repository is released under the MIT License. Users should also respect any requirements inherited from the GLM-5.2 base model and from dependencies used by the serving harness.

Citation

bibtex
@misc{mindlab2026macaronv1,
  author = {{Mind Lab}},
  title = {Introducing Macaron-V1},
  year = {2026},
  howpublished = {Mind Lab: A Lab for Experiential Intelligence},
  note = {https://macaron.im/mindlab/research/introducing-macaron-v1}
}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

mindlab-research

Model Tree

Base

zai-org/GLM-5.2

Fine-tuned

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Container

Explore FriendliAI today

Get started Talk to an engineer

Highlights

A 748B-parameter flagship model, consisting of a 744B GLM-5.2 base model and four 1B-parameter LoRA specialists across Chat, Agent, Coding, and GenUI.
The first model to be post-trained on GLM-5.2, moving Macaron's personal-intelligence stack beyond Macaron-V1-Preview.
Model-and-harness co-design: post-trained with MinT and MindForge for production-aligned routing, tool use, UI4A Generative UI, and agent workflows.
Long-context post-training infrastructure: the V1 training stack incorporates LongStraw for multi-million-token RL execution, with Venti supporting a 1M context length.
Broad evaluation across personal intelligence, agentic tasks, coding, terminal use, and Generative UI; Macaron V1 leads the listed baselines on ChatBench, LivingBench, PinchBench, TerminalBench 2.1, and UI4ABench.

Model Overview

Table with columns: Field, Value
Field	Value
Model name	Macaron-V1-Venti
Organization	MindLab Research
Release family	Macaron-V1
Base model	GLM-5.2
Architecture	GLM-5.2 base + Mixture of LoRA (MoL) specialists
Parameter footprint	748B total: 744B base + 4 x 1B LoRA specialist parameters
Specialists	L0 Chat, L1 Agent, L2 Coding, L3 GenUI (1B each)
Post-training system	MinT + MindForge
Primary domains	Personal intelligence, tool use, coding, Generative UI
Context length	1M
Precision / serving format	BF16 base checkpoint with routed LoRA serving
License	MIT

Mixture of LoRA (MoL) Architecture

Table with columns: Adapter, Role, Description
Adapter	Role	Description
`l0`	Chat	Conversational and instruction-following backbone; entry point for routing.
`l1`	Agent	Personal-life agent tasks, heavy tool use, long-horizon planning, and dynamic workflows.
`l2`	Coding	Code understanding, SWE tasks, terminal use, and repository workflows.
`l3`	GenUI	UI4A rendering and UI-driven action.

Evaluation

Macaron-V1 benchmark results

Table with columns: Benchmark, Macaron V1, GLM 5.2, GPT 5.5, Claude Opus 4.8, Gemini 3.1 Pro, Qwen 3.7 Max, Minimax M3
Benchmark	Macaron V1	GLM 5.2	GPT 5.5	Claude Opus 4.8	Gemini 3.1 Pro	Qwen 3.7 Max	Minimax M3
ChatBench	58.3	54.5	55.5	52.8	52.0	52.5	49.1
LivingBench	64.0	60.5	61.9

Higher is better for all scores shown in the chart and table.

Evaluation Protocols

The headline table reports aggregate scores from the Macaron-V1 evaluation suite covering personal intelligence, agentic tool use, coding, terminal workflows, and Generative UI.

The full benchmark methodology will be released with the technical report.

Usage

Hosted API

The hosted API is available at https://mintcn.macaron.xin/. Use the site for current model names, authentication, pricing, and rate-limit details.

For OpenAI-compatible deployments, requests follow the standard chat-completions shape:

bash
curl https://mintcn.macaron.xin/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <api-key>" \
  -d '{
    "model": "Macaron-V1-Venti",
    "messages": [
      {"role": "user", "content": "Create a compact dashboard UI for tracking weekly fitness goals."}
    ],
    "temperature": 0.2,
    "max_tokens": 2048
  }'

Mixture of LoRA (MoL) Serving

See the MoL serving repository for more details.

Macaron Artifacts

Install it as a plugin in the agent runtime you use:

text
# Claude Code
/plugin marketplace add https://github.com/MindLab-Research/macaron-artifacts
/plugin install macaron@macaron

bash
# Codex
codex plugin marketplace add https://github.com/MindLab-Research/macaron-artifacts
codex plugin add macaron@macaron

text
# Kimi Code
/plugins install https://github.com/MindLab-Research/macaron-artifacts
/reload

The WebUI can be configured from its settings page, or through environment variables:

bash
MACARON_API_BASE=https://mintcn.macaron.xin/v1
MACARON_API_KEY=<api-key>
MACARON_MODEL=Macaron-V1-Venti

License

This repository is released under the MIT License. Users should also respect any requirements inherited from the GLM-5.2 base model and from dependencies used by the serving harness.

Citation

bibtex
@misc{mindlab2026macaronv1,
  author = {{Mind Lab}},
  title = {Introducing Macaron-V1},
  year = {2026},
  howpublished = {Mind Lab: A Lab for Experiential Intelligence},
  note = {https://macaron.im/mindlab/research/introducing-macaron-v1}
}

Macaron-V1-Venti

README

Highlights

Model Overview

Mixture of LoRA (MoL) Architecture

Evaluation

Evaluation Protocols

Usage

Hosted API

Mixture of LoRA (MoL) Serving

Macaron Artifacts

License

Citation

Explore FriendliAI today

README

Highlights

Model Overview

Mixture of LoRA (MoL) Architecture

Evaluation

Evaluation Protocols

Usage

Hosted API

Mixture of LoRA (MoL) Serving

Macaron Artifacts

License

Citation