Mind Lab Toolkit (MinT)
Get started

Supported Models

MinT serves base models from two lineup pools, separated by access plan, plus a broader technically-compatible set you can request access to:

  • Community Lineup — available on the shared hosted endpoint at mint.macaron.xin via API-key request.
  • Enterprise-only Lineup — available via Enterprise plan capacity reservation on a dedicated cluster.

Community Lineup

These are the models with provisioned capacity and explicit test coverage in mint-quickstart-alpha. Use one of these for a smoke run if you have no preference.

FamilyVariantDefault in scriptsTested algorithmsNotes
Qwen3Qwen/Qwen3-0.6ByesSFT, GRPOLightweight default. Quickstart, custom_reward, custom_loss, sampling_log all run on this.
Qwen3Qwen/Qwen3-30B-A3B-Instruct-2507optionalSFT, GRPOMid-scale instruction following.
Qwen3Qwen/Qwen3-235B-A22B-Instruct-2507noSFT, GRPOLarge-scale instruction tuning. Volcano A800 cluster: inference_tp=16, train_tp=4, train_pp=1, train_ep=8.
Qwen3Qwen/Qwen3-235B-A22B-Thinking-2507noSFT, GRPOReasoning / chain-of-thought. Same cluster shape as Instruct.
OpenPImintx.OPENPI_FAST_MODEL (constant)yes for VLAVLA via SDK / HTTPEmbodied-agent track. See VLA.

Override the default by setting MINT_BASE_MODEL before running any quickstart script:

export MINT_BASE_MODEL=Qwen/Qwen3-30B-A3B-Instruct-2507
python quickstart/quickstart.py

Enterprise-only Lineup

These models require an Enterprise plan. Capacity is provisioned per customer on a dedicated cluster — they are not available on the Community shared endpoint. Canonical Hugging Face IDs are confirmed at the time of capacity provisioning.

FamilyVariantTested algorithmsNotes
GLMGLM-5SFT, RLZhipu GLM-5 family. Provisioned on customer cluster on request.
GLMGLM-5.1SFT, RLSuccessor to GLM-5; capacity reserved per customer.
KimiKimi-K2SFT, RLMoonshot Kimi-K2. Long-context workloads.
KimiKimi-K2.5SFT, RLSuccessor to Kimi-K2.
DeepSeekDeepSeek-V3SFT, RLDeepSeek V3 base model.

To reserve capacity for any of these, email sales@mindlab.ltd or Schedule a Demo and mention the model and workload class.

Technically Compatible

The MinT server endpoint accepts any HuggingFace-hub-style model string that maps to one of the supported transformer architecture families below. Lineup is the explicitly-tested subset. Other families known to work in principle:

  • Qwen series (Qwen2.5, Qwen3 — Instruct, Thinking, Coder variants)
  • Llama 3.x family
  • Gemma 2.x and 3.x
  • DeepSeek family

There is no in-repo evidence of these being run end-to-end on MinT today. If you need one of them on the lineup with provisioned capacity, request access (below).

Request a Model

If a model you need is not listed:

VLM (Vision-Language Model) base models are tracked separately as a server capability — see the VLM page for the current state.

How to know what your endpoint actually serves. A successful preflight returns a capabilities.supported_models list. The default quickstart.py prints Auth preflight: OK (N supported models) — call service_client.get_server_capabilities() from your own script to enumerate them.

On this page