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

# Diffusion Language Models (dLLMs)

Diffusion language models (dLLMs) generate text by **denoising** rather than by using left-to-right autoregression. A fixed-length response "canvas" is corrupted and then iteratively refined, so tokens are produced in parallel and can be revised across steps. NeMo AutoModel supports fine-tuning block-diffusion dLLMs with the same recipe-driven FSDP2 and expert parallel training stack used for LLMs and VLMs.

## Supported Models

LLaDA, LLaDA2, Nemotron-Labs-Diffusion, and DFlash load through their Hugging Face remote-code implementations. DiffusionGemma has a native NeMo AutoModel implementation, and I-DLM converts a supported autoregressive checkpoint with a diffusion training objective.

This table combines recipe-backed checkpoints with documented model families. Dates show when the current checkpoint first appeared in a recipe, or when a documentation-only family page was added. See the [combined model support log](/model-coverage/release-log) for recipe-backed checkpoints of every model type.

| Date       | Model                                                                                  | Architectures                                                      | Recipe                                                                                                          |
| :--------- | :------------------------------------------------------------------------------------- | :----------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------- |
| 2026-07-30 | [Qwen3-8B](/model-coverage/dllm/qwen/qwen3-idlm)                                       | `Qwen3ForCausalLM` with the I-DLM objective                        | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/dllm_sft/qwen3_8b_idlm.yaml)               |
| 2026-06-10 | [Diffusiongemma-26B-A4B-it](/model-coverage/dllm/google/diffusiongemma)                | `DiffusionGemmaForBlockDiffusion`                                  | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/dllm_sft/diffusion_gemma_lora.yaml)        |
| 2026-06-03 | [Qwen3-4B-DFlash-b16](/model-coverage/dllm/z-lab/dflash)                               | `DFlashDraftModel` with Hugging Face `trust_remote_code`           | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/dllm_sft/dflash_sft.yaml)                  |
| 2026-06-03 | [LLaDA2.1-mini](/model-coverage/dllm/inclusionai/llada2)                               | `LLaDA2MoeModelLM` with Hugging Face `trust_remote_code`           | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/dllm_sft/llada2_sft.yaml)                  |
| 2026-05-23 | [Nemotron-Labs-Diffusion-8B-Base](/model-coverage/dllm/nvidia/nemotron-labs-diffusion) | `NemotronLabsDiffusionModel` with Hugging Face `trust_remote_code` | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/dllm_sft/nemotron_labs_diffusion_sft.yaml) |
| 2026-04-04 | [LLaDA-8B-Base](/model-coverage/dllm/gsai-ml/llada)                                    | `LLaDAModelLM` with Hugging Face `trust_remote_code`               | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/dllm_sft/llada_sft.yaml)                   |

## Fine-Tuning

The [dLLM Fine-Tuning Guide](/recipes-e2e-examples/dllm-fine-tuning) provides the complete recipe walkthrough for all four families. The [DiffusionGemma Fine-Tuning Guide](/recipes-e2e-examples/diffusiongemma) describes the block-diffusion training objective (uniform random token corruption without `[MASK]`), self-conditioning, and the supported feature set (SFT, LoRA, expert parallelism, and activation checkpointing).