# GR00T-N1.6-3B by NVIDIA: Open-Weight Model Source: https://savrn.com/models/gr00t-n1-6-3b Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve GR00T-N1.6-3B (3.3B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 6.6 GB | 7.9 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 3.3 GB | 3.9 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 1.6 GB | 2.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 23, 2026. [GR00T-N1.6-3B on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/gr00t-n1-6-3b/gpus) ## Model Card NVIDIA Isaac GR00T N1.6 is an open vision-language-action (VLA) model for generalized humanoid robot skills. This cross-embodiment model takes multimodal input, including language and images, to perform manipulation tasks in diverse environments. GR00T N1.6 is trained on a diverse mixture of robot data including bimanual, semi-humanoid and an expansive humanoid dataset, consisting of real captured data, synthetic data generated using the components of NVIDIA Isaac GR00T Blueprint. It is adaptable through post-training for specific embodiments, tasks and environments. The neural network architecture of GR00T N1.6 is a combination of vision-language foundation model and diffusion transformer… Excerpt from the card by NVIDIA. ## Configuration Architecture Gr00tN1d6 Hidden size 1,024 Stored precision bfloat16 Model type Gr00tN1d6 ## Identity and Version Repository nvidia/GR00T-N1.6-3B Publisher NVIDIA Task Robotics Modality Control Library Not stated by the source Parameters 3.3B parameters Languages Not stated by the source Revision d0814e7ecb19202e7c8468b46098b0b7ef3a6d61 First published 2025-12-01 Last updated 2025-12-15 ## Files and Weights 13 files, 6.6 GB in total. The weights are 2 files totalling 6.6 GB in safetensors. Weights2 files · 6.6 GB Configuration5 files · 396.0 KB Documentation5 files · 16.0 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model-00001-of-00002.safetensors | Weights | 5.0 GB | 9710d31d331b | | model-00002-of-00002.safetensors | Weights | 1.6 GB | eb79bbd78930 | | config.json | Configuration | 1.8 KB | — | | embodiment_id.json | Configuration | 148 B | — | | model.safetensors.index.json | Configuration | 121.8 KB | — | | processor_config.json | Configuration | 9.3 KB | — | | statistics.json | Configuration | 262.8 KB | — | | EXPLAINABILITY.md | Documentation | 2.5 KB | — | | LICENSE | Documentation | 4.1 KB | — | | PRIVACY.md | Documentation | 551 B | — | | README.md | Documentation | 7.8 KB | — | | SAFETY_and_SECURITY.md | Documentation | 1.1 KB | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License Not stated by the source Access Open weights, no gate Download size 6.6 GB [Download from NVIDIA](https://huggingface.co/nvidia/GR00T-N1.6-3B) Released by NVIDIA through its official repository on Hugging Face. ## Built From - Described by [arXiv:2410.24164](https://savrn.com/papers/0-a-vision-language-action-flow-model-for-general-robot-control) - Described by arXiv:2504.15271 - Trained on (disclosed) [nvidia/PhysicalAI-Robotics-GR00T-X-Embodiment-Sim](https://savrn.com/datasets/physicalai-robotics-gr00t-x-embodiment-sim) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 6.6 GB | | 16-bit | 6.6 GB | | 8-bit | 3.3 GB | | 4-bit | 1.6 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About GR00T-N1.6-3B ### How much GPU memory does GR00T-N1.6-3B need? About 7.9 GB at 16-bit and 2 GB at 4-bit: the weights (3.3B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run GR00T-N1.6-3B on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ## Similar Models Model · Robotics ### [INTACT-pi0-finetune-bridge](https://savrn.com/models/intact-pi0-finetune-bridge) [Juexiao Zhang](https://savrn.com/model-publishers/juexzz) This repository contains a checkpoint of the Pi0 model (HF implementation | Paper) finetuned on the BridgeV2 dataset for robotic manipulation tasks. The model is later used for testing on the Simpler Environment and our INTACT Probing Suite for the generalization boundaries of VLA models. Paper: From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models Or directly in python with Lerobot, see blow: First, install lerobot Then For more details please refer to our paper and code Checkpoint choice After training 15 epochs, we sweep the checkpoint at epoch 1, 2, 3, 4, 5, 10, 15 for performance on the original 4 Bridge tasks in the SimplerEnv, and choose… Open weights apache-2.0 3.2B parameters transformers [View model](https://savrn.com/models/intact-pi0-finetune-bridge) Model · Robotics ### [actuator_unboxing_speedcond_t2_fullft_bs256](https://savrn.com/models/actuator-unboxing-speedcond-t2-fullft-bs256) [Dream Machines](https://savrn.com/model-publishers/dreammachines) Full fine-tune of lerobot/pi05base on a bimanual actuator-unboxing task, with a speed token in the text prompt: Part of a check whether pi0.5 can be conditioned through text tokens, as a precursor to advantage conditioning (RECAP, π0.6). Data (not on the Hub): 198 teleoperated episodes labelled slow, merged with 437 episodes of the same task demonstrated about 1.75× faster in another session, labelled fast (635 episodes, 371,523 frames; 50 fps, three 224×224 cameras, 14-D state and action). 30 % of training samples get unknown, the null prompt for classifier-free guidance. Training: 4,400 steps (about 3 epochs), batch 256, learning rate 5e-5, 10 % linear warm-up, cosine decay over the last… Open weights 3.4B parameters lerobot [View model](https://savrn.com/models/actuator-unboxing-speedcond-t2-fullft-bs256) Model · Robotics ### [actuator_unboxing_speedcond_t1_fullft_bs256](https://savrn.com/models/actuator-unboxing-speedcond-t1-fullft-bs256) [Dream Machines](https://savrn.com/model-publishers/dreammachines) Full fine-tune of lerobot/pi05base on a bimanual actuator-unboxing task, with a speed token in the text prompt: Part of a check whether pi0.5 can be conditioned through text tokens, as a precursor to advantage conditioning (RECAP, π0.6). Data (not on the Hub): 198 teleoperated episodes (50 fps, three 224×224 cameras, 14-D state and action) labelled slow, plus two 2× copies of every episode that keep only the even or only the odd frames, labelled fast (594 episodes, 348,616 frames). Slow and fast samples show the same images, so only the token tells them apart. 30 % of training samples get unknown, the null prompt for classifier-free guidance. Training: 4,000 steps (about 3 epochs), batch… Open weights 3.4B parameters lerobot [View model](https://savrn.com/models/actuator-unboxing-speedcond-t1-fullft-bs256) Model · Robotics ### [GR00T-N1.7-ForceBenchmark-MoE-vasev6-Transformer-30K-20260926](https://savrn.com/models/gr00t-n1-7-forcebenchmark-moe-vasev6-transformer-30k-20260926) [Linqi Han](https://savrn.com/model-publishers/hanlinqi) This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeforcetransformertuningobs2h1020260926223332/vasev6k12s1e6f384xformer/vasev6/moe/checkpoint-30000. Open weights 3.2B parameters [View model](https://savrn.com/models/gr00t-n1-7-forcebenchmark-moe-vasev6-transformer-30k-20260926) Model · Robotics ### [GR00T-N1.7-ForceBenchmark-MoE-whiteboardv9-Transformer-30K-20260926](https://savrn.com/models/gr00t-n1-7-forcebenchmark-moe-whiteboardv9-transformer-30k-20260926) [Linqi Han](https://savrn.com/model-publishers/hanlinqi) This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeforcetransformertuningobs2h1020260926223332/whiteboardv9k8s1e6f384xformer/whiteboardv9/moe/checkpoint-30000. Open weights 3.2B parameters [View model](https://savrn.com/models/gr00t-n1-7-forcebenchmark-moe-whiteboardv9-transformer-30k-20260926) Model · Robotics ### [GR00T-N1.7-ForceBenchmark-MoE-usb-Transformer-30K-20260926](https://savrn.com/models/gr00t-n1-7-forcebenchmark-moe-usb-transformer-30k-20260926) [Linqi Han](https://savrn.com/model-publishers/hanlinqi) This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeforcetransformertuningobs2h1020260926223332/usbk6s1e4f384xformer/usb/moe/checkpoint-30000. Open weights 3.2B parameters [View model](https://savrn.com/models/gr00t-n1-7-forcebenchmark-moe-usb-transformer-30k-20260926) ## NVIDIA [All models and datasets](https://savrn.com/model-publishers/nvidia) ## Versions - [d0814e7ecb19](https://savrn.com/models/gr00t-n1-6-3b/versions/d0814e7ecb19) · current 2026-09-18 ## Explore More - [All robotics models](https://savrn.com/models/tasks/robotics) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-20. - [NVIDIA website](https://build.nvidia.com/models) - [Hugging Face record](https://huggingface.co/nvidia/GR00T-N1.6-3B) - [How the hub is built](https://savrn.com/model-hub/methodology)