> This page is for version Nightly (default). > For other versions, use one of these documentation indexes: > - Nightly (default): https://docs.nvidia.com/nemo/automodel/nightly/llms.txt > - Latest: https://docs.nvidia.com/nemo/automodel/latest/llms.txt > - 0.7.0 · 26.10: https://docs.nvidia.com/nemo/automodel/v0.7/llms.txt > - 0.5.0 · 26.06: https://docs.nvidia.com/nemo/automodel/v0.5/llms.txt > - 0.4.0 · 26.04: https://docs.nvidia.com/nemo/automodel/v0.4/llms.txt > 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-Bolt-E4B-4GB-BF16 > Fine-tune NVIDIA-Nemotron-3.5-Bolt-E4B-4GB-BF16 with NeMo AutoModel using the checked-in full-parameter and LoRA recipes for the Gemma 4 E4B architecture. [NVIDIA-Nemotron-3.5-Bolt-E4B-4GB-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB-BF16) is a small language model post-trained by NVIDIA from [Gemma-4-E4B-it](https://huggingface.co/google/gemma-4-E4B-it). It keeps the Gemma 4 E4B architecture and refreshes the weights and the chat template. The BF16 release is the full-precision checkpoint intended for customization, post-training, and evaluation. NeMo AutoModel provides full-parameter and Low-Rank Adaptation (LoRA) recipes that load the checkpoint through the native Gemma 4 path and apply the chat template shipped with the checkpoint. Set up NeMo AutoModel with the [latest container](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo-automodel) or follow the [installation instructions](/nemo/automodel/get-started/installation). ## Fine-Tune NVIDIA-Nemotron-3.5-Bolt-E4B-4GB-BF16 From the repository root, run the 8-GPU full-parameter recipe: ```bash uv run automodel examples/vlm_finetune/nemotron_3_5_bolt/nemotron_3_5_bolt_e4b.yaml --nproc-per-node 8 ``` Or run the 2-GPU LoRA recipe: ```bash uv run automodel examples/vlm_finetune/nemotron_3_5_bolt/nemotron_3_5_bolt_e4b_peft.yaml --nproc-per-node 2 ``` ## Choose a Workflow | Goal | Start Here | | ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | Full-parameter fine-tuning on MedPix-VQA | Use [nemotron_3_5_bolt_e4b.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/nemotron_3_5_bolt/nemotron_3_5_bolt_e4b.yaml). | | LoRA fine-tuning on MedPix-VQA | Use [nemotron_3_5_bolt_e4b_peft.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/nemotron_3_5_bolt/nemotron_3_5_bolt_e4b_peft.yaml). | ### Configuration | Setting | Full-parameter recipe | LoRA recipe | | -------------- | ------------------------------------------- | ------------------------------------------------------------- | | Hardware | 8 NVIDIA H100 80GB GPUs | 2 NVIDIA H100 80GB GPUs | | Strategy | FSDP2; `tp_size=1`, `cp_size=1` | FSDP2; `tp_size=1`, `cp_size=1` | | Batch | `local_batch_size=1`, `global_batch_size=8` | `local_batch_size=1`, `global_batch_size=8` | | Attention | Eager | SDPA | | Adapter | None | LoRA `dim=16`, `alpha=32` on the language model linear layers | | Optimizer | AdamW, `lr=1e-5` | AdamW, `lr=2e-4`, cosine decay | | Frozen modules | Vision and audio towers | Vision and audio towers, plus the base weights | Both recipes set `dataset.chat_template` and `validation_dataset.chat_template` to the chat template shipped with the checkpoint, so the training prompts match the template the model was post-trained with. The template exposes the same controls as the model card: `enable_thinking` switches reasoning on or off, and `conversational_mode` adds the spoken-conversation system instruction for concise, low-formatting replies. ## Model Reference ### Model Architecture | Property | Value | | ------------------------- | --------------------------------------------------------------------------------------------------------------------- | | Developer | NVIDIA Corporation | | Base model | [`google/gemma-4-E4B-it`](https://huggingface.co/google/gemma-4-E4B-it) | | Architecture type | Gemma 4 | | Network architecture | Gemma-4-E4B | | Hugging Face architecture | `Gemma4ForConditionalGeneration` | | Total parameters | 8B (4B effective) | | Precision | BF16 | | Context length | Input up to 64K tokens; output up to 64K tokens | | Inputs and outputs | Text in, text out | | Reasoning mode | Chat-template controls (`enable_thinking=True/False`) and a runtime thinking budget | | Conversational mode | Chat-template control (`conversational_mode=True/False`) | | Recommended sampling | Temperature 1.0, top_p 0.95 in both thinking modes | | Best for | Local voice and device assistants, interactive personas, and embedded interfaces | | License | [OpenMDW-1.1](https://github.com/OpenMDW/OpenMDW/blob/main/1.1/LICENSE.OpenMDW-1.1) | | Checkpoint | [`nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB-BF16`](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB-BF16) | ### Training Methodology The model was post-trained from Gemma-4-E4B-it with multi-environment reinforcement learning using Group Relative Policy Optimization (GRPO) across instruction following, multi-step tool use, multi-turn conversations, and structured-output environments, on an asynchronous RL architecture that decouples training from inference. The reinforcement learning used [NeMo RL](https://github.com/NVIDIA-NeMo/RL) and [NeMo Gym](https://github.com/NVIDIA-NeMo/Gym). ### Prompting Guidelines The model card recommends the following for conversational and agentic applications: * Store persistent behavior constraints and operational guidelines in system prompts, with explicit headers for roles, tasks, tool configs, and formatting rules. * Write unambiguous, verifiable instructions and use explicit constraints such as "limit responses to 1-2 sentences" instead of vague requests. * Adhere strictly to standard `system/user/assistant/tool` turn sequences and avoid synthetic outputs in `assistant` turns. * Set `conversational_mode=True` for concise, low-formatting outputs suited to spoken interaction. ### Available Models * [`nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB-BF16`](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB-BF16) (HF BF16) * [`nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB`](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB) (Q4_K_M GGUF for inference) ## Related Resources * [Gemma 4 Fine-Tuning Guide](/nemo/automodel/recipes-e2e-examples/gemma-4) * [NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16](/nemo/automodel/model-coverage/vision-language-models/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16)