For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Python module

max.pipelines.architectures

MAX includes built-in support for a wide range of model architectures. Each architecture module registers a SupportedArchitecture instance that tells the pipeline system how to load, configure, and execute a particular model family.

Text generation

`deepseekV2`	DeepSeek-V2 mixture-of-experts architecture for text generation.
`deepseekV3`	DeepSeek-V3 mixture-of-experts architecture for text generation.
`deepseekV3_2`	DeepSeek-V3.2 mixture-of-experts architecture for text generation.
`deepseekV3_nextn`	DeepSeek-V3 NextN multi-token prediction draft model for speculative decoding.
`dflash_llama3`	DFlash draft model for Llama3-family targets.
`eagle3_deepseekV3`	DeepseekV3 + Eagle3 speculator pipeline.
`eagle_llama3`	EAGLE speculative decoding draft model for Llama 3.
`exaone`	EXAONE architecture, builds on `llama3`.
`exaone_modulev3`	EXAONE (eager) architecture, builds on `llama3_modulev3`.
`gemma3`	Gemma 3 transformer architecture for text generation.
`gemma3_modulev3`	Gemma 3 transformer architecture for text generation.
`gemma3multimodal`	Gemma 3 vision-language architecture for multimodal text generation.
`gemma3multimodal_modulev3`	Gemma 3 vision-language architecture for multimodal text generation.
`gemma4`	Gemma 4 vision-language architecture for multimodal text generation.
`gpt_oss`	GPT-OSS mixture-of-experts architecture for text generation.
`gpt_oss_modulev3`	GPT-OSS mixture-of-experts architecture for text generation.
`granite`	Granite architecture, builds on `llama3`.
`granite_modulev3`	Granite (eager) architecture, builds on `llama3_modulev3`.
`idefics3`	Idefics3 vision-language architecture for multimodal text generation.
`idefics3_modulev3`	Idefics3 vision-language architecture for multimodal text generation.
`internvl`	InternVL vision-language architecture for multimodal text generation.
`kimik2_5`	Kimi K2.5 mixture-of-experts architecture for text generation.
`lfm2`
`llama3`	Llama 3 transformer architecture for text generation.
`llama3_modulev3`	Llama 3 transformer architecture for text generation.
`mamba`	Mamba state-space architecture for text generation.
`minimax_m2`
`mistral`	Mistral transformer architecture for text generation.
`mistral3`	Mistral 3 vision-language architecture for multimodal text generation.
`olmo`	OLMo transformer architecture for text generation.
`olmo2`	OLMo 2 transformer architecture for text generation.
`olmo2_modulev3`	OLMo 2 transformer architecture for text generation.
`olmo3`	OLMo 3 transformer architecture for text generation.
`olmo_modulev3`	OLMo transformer architecture for text generation.
`phi3`	Phi-3 transformer architecture for text generation.
`phi3_modulev3`	Phi-3 transformer architecture for text generation.
`pixtral`	Pixtral vision-language architecture for multimodal text generation.
`pixtral_modulev3`	Pixtral vision-language architecture for multimodal text generation.
`qwen2`	Qwen2 transformer architecture for text generation.
`qwen2_5vl`	Qwen2.5-VL vision-language architecture for multimodal text generation.
`qwen3`	Qwen3 transformer architecture for text generation.
`qwen3_5`
`qwen3vl_moe`	Qwen3-VL vision-language architecture for multimodal text generation.
`step3p5`
`unified_dflash_llama3`	DFlash speculative decoding for Llama3 with unified graph compilation.
`unified_eagle_llama3`	EAGLE speculative decoding draft model for Llama 3 with unified graph compilation.
`unified_mtp_deepseekV3`	DeepSeek-V3 multi-token prediction draft model for speculative decoding with unified graph compilation.

Embeddings

`bert`	BERT sentence transformer architecture for embeddings generation.
`mpnet`	MPNet sentence transformer architecture for embeddings generation.
`mpnet_modulev3`	MPNet sentence transformer architecture for embeddings generation.
`qwen3_embedding`	Qwen3 architecture for embeddings generation.
`qwen3_embedding_modulev3`	Qwen3 architecture for embeddings generation.

Image generation

`flux2`	FLUX.2 diffusion architecture for image generation.
`qwen_image`	Qwen-Image diffusion architecture for image generation.
`qwen_image_edit`	Qwen-Image-Edit diffusion architecture for image editing.
`wan`	Wan diffusion architecture for video generation.
`z_image_modulev3`	Z-Image diffusion architecture for image generation.

Text generation​

Embeddings​

Image generation​

Text generation

Embeddings

Image generation