GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
mindlab-research
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
mindlab-research
Model Tree
Qwen/Qwen3.6-35B-A3B
Input Modalities
Output Modalities
Supported Functionality
loras/L0 through loras/L3.| Field | Value |
|---|---|
| Model name | Macaron-V1-Tall |
| Organization | MindLab Research |
| Release family | Macaron-V1 |
| Base model | Qwen3.6-35B-A3B |
| Architecture | Qwen3.6 MoE base + Mixture of LoRA (MoL) specialists |
| Checkpoint contents | BF16 base checkpoint + four LoRA adapters |
| Specialists | L0 Chat, L1 Agent, L2 Coding, L3 GenUI |
| LoRA rank | 64 |
| Post-training system | MinT + MindForge |
| Primary domains | Personal intelligence, tool use, coding, Generative UI |
| Context length | 262K |
| Text config | 40 layers, 2048 hidden size, 16 attention heads, 2 KV heads, 256 experts, 8 experts per token |
| Precision / serving format | BF16 base checkpoint with routed LoRA serving |
| License | MIT |
| Adapter | Role | Description |
|---|---|---|
loras/L0 | Chat | Conversational and instruction-following backbone; entry point for routing. |
loras/L1 | Agent | Personal-life agent tasks, heavy tool use, long-horizon planning, and dynamic workflows. |
loras/L2 | Coding | Code understanding, SWE tasks, terminal use, and repository workflows. |
loras/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.
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-Tall","messages": [{"role": "user", "content": "Create a compact dashboard UI for tracking weekly fitness goals."}],"temperature": 0.2,"max_tokens": 2048}'
This repository contains the base checkpoint at the repository root and the Macaron LoRA specialists under loras/. Load the base checkpoint with a Transformers version that supports the Qwen3.6 / Qwen3.5 MoE architecture.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerrepo_id = "mindlab-research/Macaron-V1-Tall"tokenizer = AutoTokenizer.from_pretrained(repo_id,trust_remote_code=True,)model = AutoModelForCausalLM.from_pretrained(repo_id,torch_dtype=torch.bfloat16,device_map="auto",trust_remote_code=True,)model.eval()
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 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.
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.
This repository is released under the MIT License. Users should also respect any requirements inherited from the Qwen3.6-35B-A3B base model and from dependencies used by the serving harness.
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}}