> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server.

# Vision Language Models

## Docs

- [Vision Language Models (VLMs)](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/overview.md): 
- [Cohere Labs](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/coherelabs.md): Browse NeMo AutoModel coverage for Cohere Labs vision language models.
- [North-Micro-Vision-Instruct](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/coherelabs/North-Micro-Vision-Instruct.md): Fine-tune North-Micro-Vision-Instruct for image-text tasks with NeMo AutoModel using the checked-in two-GPU LoRA recipe.
- [DeepSeek AI](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/deepseek-ai.md): Browse NeMo AutoModel coverage for DeepSeek AI vision language models.
- [DeepSeek-V4-Flash-Vision-Exp](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp.md): Use NeMo AutoModel to fine-tune DeepSeek-V4-Flash-Vision-Exp for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [DeepSeek-V4.1-Flash](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/deepseek-ai/DeepSeek-V4.1-Flash.md): Use NeMo AutoModel to fine-tune DeepSeek-V4.1-Flash for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Google](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/google.md): Browse NeMo AutoModel coverage for Google vision language models.
- [gemma-3-4b-it](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/google/gemma-3-4b-it.md): Fine-tune gemma-3-4b-it for image-text tasks with NeMo AutoModel using checked-in full-parameter, LoRA, and distributed recipes.
- [gemma-3n-E4B-it](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/google/gemma-3n-E4B-it.md): Fine-tune gemma-3n-E4B-it for image-text-to-text tasks with NeMo AutoModel using checked-in recipes and distributed settings.
- [gemma-4-26B-A4B-it](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/google/gemma-4-26B-A4B-it.md): Fine-tune gemma-4-26B-A4B-it for image-text-to-text tasks with NeMo AutoModel using checked-in recipes and distributed settings.
- [gemma-4-31B-it](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/google/gemma-4-31B-it.md): Fine-tune gemma-4-31B-it for image-text tasks with NeMo AutoModel using checked-in full-parameter, LoRA, tensor-parallel, and pipeline-parallel recipes.
- [gemma-4-E2B-it](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/google/gemma-4-E2B-it.md): Fine-tune gemma-4-E2B-it for image-text-to-text tasks with NeMo AutoModel using checked-in recipes and distributed settings.
- [gemma-4-E4B-it](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/google/gemma-4-E4B-it.md): Fine-tune gemma-4-E4B-it for image-text-to-text tasks with NeMo AutoModel using checked-in recipes and distributed settings.
- [HuggingFaceTB](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/huggingfacetb.md): Browse NeMo AutoModel coverage for models published under the HuggingFaceTB Hugging Face organization.
- [SmolVLM-Instruct](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/huggingfacetb/SmolVLM-Instruct.md): Reference SmolVLM-Instruct checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.
- [LLaVA HF](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/llava-hf.md): Browse NeMo AutoModel coverage for LLaVA HF vision language models.
- [llava-1.5-7b-hf](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/llava-hf/llava-1.5-7b-hf.md): Reference llava-1.5-7b-hf checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.
- [LMMS Lab](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/lmms-lab.md): Browse NeMo AutoModel coverage for LMMS Lab vision language models.
- [LLaVA-OneVision-1.5-4B-Instruct](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/lmms-lab/LLaVA-OneVision-1.5-4B-Instruct.md): Use LLaVA-OneVision-1.5-4B-Instruct with NeMo AutoModel for vision-language fine-tuning, including checkpoints, runnable recipes, setup, and reference details.
- [LLaVA-OneVision-1.5-8B-Instruct](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/lmms-lab/LLaVA-OneVision-1.5-8B-Instruct.md): Use NeMo AutoModel to fine-tune LLaVA-OneVision-1.5-8B-Instruct for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Meta](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/meta.md): Browse NeMo AutoModel coverage for Meta vision language models.
- [Llama-4-Scout-17B-16E-Instruct](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/meta/Llama-4-Scout-17B-16E-Instruct.md): Reference Llama-4-Scout-17B-16E-Instruct checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.
- [Meta Models](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/meta-models.md): Browse NeMo AutoModel coverage for models published under the meta-models Hugging Face organization.
- [Muse-Glimmer-30B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/meta-models/Muse-Glimmer-30B.md): Use Muse-Glimmer-30B with NeMo AutoModel for vision-language fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.
- [Muse-Spark-open-816B-A42B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/meta-models/Muse-Spark-open-816B-A42B.md): Fine-tune meta-models/Muse-Spark-open-816B-A42B with NeMo AutoModel using MedPix vision-language recipes and packed Tulu 3 context parallelism.
- [MiniMax AI](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/minimax.md): Browse NeMo AutoModel coverage for MiniMax AI vision language models.
- [MiniMax-M3](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/minimax/MiniMax-M3.md): Fine-tune MiniMax-M3 text-only on Tulu-3 or with MedPix vision-language data using NeMo AutoModel supervised fine-tuning recipes.
- [Mistral AI](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/mistralai.md): Browse NeMo AutoModel coverage for Mistral AI vision language models.
- [Devstral-2-123B-Instruct-2512](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/mistralai/Devstral-2-123B-Instruct-2512.md): Fine-tune Devstral-2-123B-Instruct-2512 for text generation with NeMo AutoModel using the checked-in single-node tensor-parallel LoRA recipe.
- [Ministral-3-14B-Reasoning-2512](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/mistralai/Ministral-3-14B-Reasoning-2512.md): Use NeMo AutoModel to fine-tune Ministral-3-14B-Reasoning-2512 for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Ministral-3-3B-Instruct-2512](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/mistralai/Ministral-3-3B-Instruct-2512.md): Reference Ministral-3-3B-Instruct-2512 checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.
- [Ministral-3-8B-Reasoning-2512](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/mistralai/Ministral-3-8B-Reasoning-2512.md): Use NeMo AutoModel to fine-tune Ministral-3-8B-Reasoning-2512 for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Mistral-Medium-3.5-128B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/mistralai/Mistral-Medium-3.5-128B.md): Use NeMo AutoModel to fine-tune Mistral-Medium-3.5-128B for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Mistral-Small-4-119B-2603](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/mistralai/Mistral-Small-4-119B-2603.md): Use Mistral-Small-4-119B-2603 with NeMo AutoModel for vision-language fine-tuning, with documented checkpoints, runnable recipes, setup, and model reference details.
- [Moonshot AI](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/moonshotai.md): Browse NeMo AutoModel coverage for Moonshot AI vision language models.
- [Kimi-K2.5](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/moonshotai/Kimi-K2.5.md): Use NeMo AutoModel to fine-tune Kimi-K2.5 for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Kimi-K3](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/moonshotai/Kimi-K3.md): Use Kimi-K3 with NeMo AutoModel for vision-language fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.
- [Kimi-VL-A3B-Instruct](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/moonshotai/Kimi-VL-A3B-Instruct.md): Use Kimi-VL-A3B-Instruct with NeMo AutoModel for vision-language fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.
- [NVIDIA](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/nvidia.md): Browse NeMo AutoModel coverage for NVIDIA vision language models.
- [NVIDIA-Nemotron-Parse-v1.1](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/nvidia/NVIDIA-Nemotron-Parse-v1.1.md): Use NVIDIA-Nemotron-Parse-v1.1 with NeMo AutoModel for vision-language fine-tuning, with documented checkpoints, runnable recipes, setup, and model reference details.
- [OpenGVLab](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/opengvlab.md): Browse NeMo AutoModel coverage for models published under the OpenGVLab Hugging Face organization.
- [InternVL3_5-4B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/opengvlab/InternVL3_5-4B.md): Use InternVL3_5-4B with NeMo AutoModel for vision-language fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.
- [Qwen](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen.md): Browse NeMo AutoModel coverage for Qwen vision language models.
- [Qwen2.5-VL-3B-Instruct](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen2.5-VL-3B-Instruct.md): Use Qwen2.5-VL-3B-Instruct with NeMo AutoModel for vision-language fine-tuning, with documented checkpoints, runnable recipes, setup, and model reference details.
- [Qwen3-VL-235B-A22B-Instruct](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen3-VL-235B-A22B-Instruct.md): Use NeMo AutoModel to fine-tune Qwen3-VL-235B-A22B-Instruct for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Qwen3-VL-30B-A3B-Instruct](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen3-VL-30B-A3B-Instruct.md): Use NeMo AutoModel to fine-tune Qwen3-VL-30B-A3B-Instruct for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Qwen3-VL-4B-Instruct](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen3-VL-4B-Instruct.md): Reference Qwen3-VL-4B-Instruct checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.
- [Qwen3-VL-8B-Instruct](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen3-VL-8B-Instruct.md): Use NeMo AutoModel to fine-tune Qwen3-VL-8B-Instruct for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Qwen3.5-122B-A10B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen3.5-122B-A10B.md): Use NeMo AutoModel to fine-tune Qwen3.5-122B-A10B for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Qwen3.5-27B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen3.5-27B.md): Use NeMo AutoModel to fine-tune Qwen3.5-27B for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Qwen3.5-35B-A3B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen3.5-35B-A3B.md): Use NeMo AutoModel to fine-tune Qwen3.5-35B-A3B for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Qwen3.5-397B-A17B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen3.5-397B-A17B.md): Use NeMo AutoModel to fine-tune Qwen3.5-397B-A17B for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Qwen3.5-4B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen3.5-4B.md): Use Qwen3.5-4B with NeMo AutoModel for vision-language fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.
- [Qwen3.5-9B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen3.5-9B.md): Use NeMo AutoModel to fine-tune Qwen3.5-9B for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Qwen3.6-27B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen3.6-27B.md): Fine-tune Qwen3.6-27B for vision-language tasks with NeMo AutoModel using checked-in full-parameter and LoRA recipes with distributed settings.
- [Qwen3.6-35B-A3B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen3.6-35B-A3B.md): Use NeMo AutoModel to fine-tune Qwen3.6-35B-A3B for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Qwen3.8-27B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/qwen/Qwen3.8-27B.md): Fine-tune Qwen3.8-27B for vision-language tasks with NeMo AutoModel using checked-in full-parameter and LoRA recipes with distributed settings.
- [StepFun AI](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/stepfun-ai.md): Browse NeMo AutoModel coverage for StepFun AI vision language models.
- [Step-3.7-Flash](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/stepfun-ai/Step-3.7-Flash.md): Fine-tune Step-3.7-Flash on MedPix with full or LoRA vision-language recipes in NeMo AutoModel for supervised image-text training.
- [Step-5-Preview](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/stepfun-ai/Step-5-Preview.md): Step-5-Preview vision-language architecture, packed context-parallel inputs, and current preprocessing scope in NeMo AutoModel.
- [Thinking Machines](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/thinkingmachines.md): Browse NeMo AutoModel coverage for Thinking Machines vision language models.
- [Inkling](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/thinkingmachines/Inkling.md): Fine-tune Inkling vision-language checkpoints with NeMo AutoModel using checked-in multi-node recipes with expert and pipeline parallelism.
- [Inkling-Small](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/thinkingmachines/Inkling-Small.md): Use NeMo AutoModel to fine-tune Inkling-Small for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.
- [Z.ai](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/thudm.md): Browse NeMo AutoModel coverage for Z.ai vision language models.
- [GLM-5.3-Flash](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/thudm/GLM-5.3-Flash.md): Fine-tune GLM-5.3-Flash for vision-language tasks with NeMo AutoModel using a checked-in packed-context and expert-parallel recipe.