> ## Documentation Index
> Fetch the complete documentation index at: https://docs.trymonte.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Models

> Supported open-weight models

A training config names its base model in `model`, as a Hugging Face ID. `--model` replaces it for one run:

```bash theme={null}
monte train support-triage --config triage-sft --data support-replies \
  --steps 200 --from-base --model Qwen/Qwen3.5-9B
```

A new base model needs its own [baselines](https://docs.trymonte.ai/evaluation/experiments.md#take-the-baselines) before it trains. A run picks its GPUs by the model's size, and [`--gpu` and `--gpus`](https://docs.trymonte.ai/commands/training#monte-train) override the choice.

## Supported Models

Every model below trains with SFT, DPO, and GRPO, and with distillation as a student when its family has a larger model with the same tokenizer. A size such as 30B-A3B is 30B total parameters, with 3B active for each token.

![](https://docs.trymonte.ai/images/models/qwen-light.svg)

Qwen3, Qwen3.5

Alibaba Qwen

![](https://docs.trymonte.ai/images/models/deepseek-light.svg)

DeepSeek

DeepSeek

![](https://docs.trymonte.ai/images/models/zai-light.svg)

GLM

Z.ai

![](https://docs.trymonte.ai/images/models/kimi-light.svg)

Kimi

Moonshot AI

![](https://docs.trymonte.ai/images/models/nvidia-light.svg)

Nemotron 3

NVIDIA

![](https://docs.trymonte.ai/images/models/openai-light.svg)

gpt-oss

OpenAI

## Choose a Model

| Use case | Recommended models |
| - | - |
| A first run, or a fast iteration on the data | A model of 1B to 9B, such as `Qwen/Qwen3-8B` |
| Multi-turn tool use | An instruct model with a tool-call chat template: Qwen3, GLM, Kimi K2, or gpt-oss |
| Reasoning before the answer | Qwen3, DeepSeek R1, Kimi K2 Thinking, or gpt-oss |
| A distillation pair | A teacher and a student from one family, which share one tokenizer vocabulary: `Qwen/Qwen3-235B-A22B` and `Qwen/Qwen3-8B` |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.