> 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. # NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 > Use NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 with NeMo AutoModel for multimodal fine-tuning, with checkpoints, recipes, setup, and reference details. [NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16) pairs a Nemotron Super NemotronH (hybrid Mamba-2 and Attention) Mixture-of-Experts (MoE) language backbone with a RADIO v2.5-H vision encoder, sharing its `NemotronH_Omni_Reasoning_V3` architecture and vision stack with [Nemotron-3-Nano-Omni](/model-coverage/omni/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16). The BF16 checkpoint has no audio encoder, so audio inputs are not supported. Set up NeMo AutoModel with the [latest container](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo-automodel) or follow the [installation instructions](/get-started/installation). ## Fine-Tune NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 From the repository root, run: ```bash uv run automodel examples/vlm_finetune/nemotron_3_5_super_vl/nemotron_3_5_super_vl_cord_v2_peft.yaml --nproc-per-node 8 ``` The Tulu-3 text recipe runs on 4 nodes: ```bash uv run automodel examples/vlm_finetune/nemotron_3_5_super_vl/nemotron_3_5_super_vl_tulu3_text_100steps.yaml --nnodes 4 --nproc-per-node 8 ``` ## Choose a Workflow | Goal | Start Here | | -------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Full SFT, text-only (vision/audio towers frozen and unused) | Use [nemotron\_3\_5\_super\_vl\_tulu3\_text\_100steps.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/nemotron_3_5_super_vl/nemotron_3_5_super_vl_tulu3_text_100steps.yaml). Dataset: Tulu-3. | | Context-parallel parity test, `cp_size=8`; text-only packs (`inject_fake_images: false`) | Use [nemotron\_3\_5\_super\_vl\_tulu3\_packed\_cp8\_100steps.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/nemotron_3_5_super_vl/nemotron_3_5_super_vl_tulu3_packed_cp8_100steps.yaml). Dataset: Tulu-3 (packed, THD). | | Low-rank adaptation (LoRA) (rank 64) on the LLM linear projections, base model frozen; receipt image to structured field tokens; single node | Use [nemotron\_3\_5\_super\_vl\_cord\_v2\_peft.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/nemotron_3_5_super_vl/nemotron_3_5_super_vl_cord_v2_peft.yaml). Dataset: CORD-v2. | ### LoRA on CORD-v2 `nemotron_3_5_super_vl_cord_v2_peft.yaml` fine-tunes the model on CORD-v2 receipt field extraction (the same task as the [NemotronOmni CORD-v2 guide](/recipes-e2e-examples/nemotron-omni)) with LoRA adapters instead of full SFT. Because the base weights are frozen, there are no fp32 master weights or optimizer states for them, so the 121B model trains on a single node of 8 H100 (`cp_size 1`, `ep_size 8`) instead of the 4 nodes that full SFT needs. | Property | Value | | ------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Low-rank adaptation (LoRA) targets | 272 linear projections: Mamba `in_proj`/`out_proj`, attention `q/k/v/o_proj`, MoE `fc1/fc2_latent_proj` and shared experts (routed experts, vision tower, projector, `lm_head` frozen) | | Trainable parameters | 177M (0.15%), rank 64, alpha 128; TE `FusedAdam` with fp32 master weights, lr 2e-4 | | Peak memory | 38.8 GiB/GPU | | Adapter checkpoint | 355 MB (`adapter_model.safetensors` + `adapter_config.json`) | | Training | 400 steps (global batch 8, 4 epochs of the 800 training receipts) in 13 min on one node; train loss 0.51 -> 0.01 | | Validation loss | 0.041 / 0.039 / 0.043 / 0.040 at steps 99 / 199 / 299 / 399 | | Field extraction (first 20 validation receipts, greedy, adapter merged into the base model) | step 199 (`LOWEST_VAL`): 8/20 exact match, mean similarity 0.954 (median 0.997), 20/20 structured outputs | ## Model Reference ### Model Architecture | Property | Value | | ------------------------- | --------------------------------------------------------------------------------- | | Task | Multimodal (Text/Image) | | Architecture | `NemotronH_Omni_Reasoning_V3` | | Parameters | 121B total (MoE, 512 routed experts, 22 active per token; 124B with the MTP head) | | Hugging Face Organization | [nvidia](https://huggingface.co/nvidia) | * `NemotronH_Omni_Reasoning_V3` reuses the same `NemotronOmniForConditionalGeneration` wrapper, vision tower, and state-dict adapter as `NemotronH_Nano_Omni_Reasoning_V3`; only the LLM sub-config scale differs (Super compared to Nano). The `sound_encoder` and `sound_projection` submodules are constructed only when the checkpoint's `sound_config` is present, so this checkpoint loads with audio disabled. ### Available Models * **NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16**: 121B total (MoE), post-trained, no audio encoder * **[NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16)**: 121B total (MoE), pretrained only, no audio encoder ## Related Resources * [VLM Fine-Tuning Guide](/recipes-e2e-examples/gemma-3-3n)