# Alpamayo-1.5-10B by NVIDIA: Open-Weight Model Source: https://savrn.com/models/alpamayo-1-5-10b Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve Alpamayo-1.5-10B (11.1B 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 | 22.2 GB | 26.6 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 | 11.1 GB | 13.3 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 | 5.5 GB | 6.6 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. [Alpamayo-1.5-10B on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/alpamayo-1-5-10b/gpus) ## Model Card Alpamayo 1.5 is a significant update to NVIDIA’s open 10B-parameter chain-of-thought reasoning VLA model, designed to be an interactive and steerable reasoning engine for the AV community. Alpamayo 1.5 is built on the Cosmos-Reason2 VLM backbone, is RL post-trained, and introduces support for navigation guidance, flexible camera counts, and user question answering. This model is ready for non-commercial use. Commercial licensing available upon request. Model weights: The model weights are released under the OpenMDW-1.1 license. Source code: Apache License 2.0, as provided in the Alpamayo 1.5 source repository. Global Researchers and autonomous-driving practitioners who are developing and… Excerpt from the card by NVIDIA, licensed openmdw-1.1. ## Configuration Architecture Alpamayo1_5 Vocabulary size 155,697 Model type alpamayo1_5 ## Identity and Version Repository nvidia/Alpamayo-1.5-10B Publisher NVIDIA Task Robotics Modality Control Library Not stated by the source Parameters 11.1B parameters Languages en Revision 7aba8293c09993f2e125c6819df05d7fa3e873ea First published 2026-03-03 Last updated 2026-08-07 ## Files and Weights 10 files, 22.2 GB in total. The weights are 5 files totalling 22.2 GB in safetensors. Weights5 files · 22.2 GB Configuration2 files · 107.8 KB Documentation2 files · 13.1 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model-00001-of-00005.safetensors | Weights | 4.9 GB | 537259bb5681 | | model-00002-of-00005.safetensors | Weights | 4.9 GB | 18841e5049b7 | | model-00003-of-00005.safetensors | Weights | 5.0 GB | e8953b27fe82 | | model-00004-of-00005.safetensors | Weights | 5.0 GB | 604f0c0f1998 | | model-00005-of-00005.safetensors | Weights | 2.3 GB | 9d889c09634e | | config.json | Configuration | 3.1 KB | — | | model.safetensors.index.json | Configuration | 104.8 KB | — | | LICENSE | Documentation | 2.6 KB | — | | README.md | Documentation | 10.4 KB | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License openmdw-1.1 Access Open weights, no gate Download size 22.2 GB [Download from NVIDIA](https://huggingface.co/nvidia/Alpamayo-1.5-10B) Released by NVIDIA through its official repository on Hugging Face. ## Built From - Derived from nvidia/Cosmos-Reason2-8B - Trained on (disclosed) [nvidia/PhysicalAI-Autonomous-Vehicles](https://savrn.com/datasets/physicalai-autonomous-vehicles) - Trained on (disclosed) nvidia/PhysicalAI-Autonomous-Vehicles-NuRec ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 22.2 GB | | 16-bit | 22.2 GB | | 8-bit | 11.1 GB | | 4-bit | 5.5 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Built on This Model - Derived from[Alpamayo-1.5-10B](https://savrn.com/models/alpamayo-1-5-10b-2) ## Questions About Alpamayo-1.5-10B ### How much GPU memory does Alpamayo-1.5-10B need? About 26.6 GB at 16-bit and 6.6 GB at 4-bit: the weights (11.1B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run Alpamayo-1.5-10B 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. ### What license is Alpamayo-1.5-10B released under? openmdw-1.1, as its publisher declares it. Read the license text before commercial use. ## Similar Models Model · Robotics ### [Alpamayo-R1-10B](https://savrn.com/models/alpamayo-r1-10b) [NVIDIA](https://savrn.com/model-publishers/nvidia) Note: Following the release of NVIDIA Alpamayo at CES 2026, Alpamayo-R1 has been renamed to Alpamayo 1. Alpamayo 1 integrates Chain-of-Causation reasoning with trajectory planning to enhance decision-making in complex autonomous-driving scenarios. Alpamayo 1 (v1.0) was developed by NVIDIA as a vision-language-action (VLA) model that bridges interpretable reasoning with precise vehicle control for autonomous-driving applications. This model is ready for non-commercial use. Commercial licensing available upon request. Model weights: The model weights are released under the OpenMDW-1.1 license. Source code: Apache License 2.0, as provided in the Alpamayo 1 source repository. Global Researchers… Open weights openmdw-1.1 11.1B parameters transformers [View model](https://savrn.com/models/alpamayo-r1-10b) Model · Robotics ### [Alpamayo-1.5-10B](https://savrn.com/models/alpamayo-1-5-10b-2) [Z Lab](https://savrn.com/model-publishers/z-lab) Flash Vision-Language-Action Inference for Autonomous Driving FlashDrive accelerates Alpamayo 1.5 — one of NVIDIA's 10B-parameter vision-language-action models for autonomous driving — by 4.7× with no loss in accuracy, through streaming inference, DFlash speculative reasoning, ParoQuant W4A8 quantization, adaptive action caching, and torch.compile. This repository mirrors the weights of nvidia/Alpamayo-1.5-10B and is the base checkpoint of the FlashDrive stack. Loading it pulls the derived companions automatically: Install FlashDrive, then load this base checkpoint — the -PARO and -DFlash companions are fetched automatically: The first call per stream only prefills the KV cache and returns… Open weights other 11.1B parameters [View model](https://savrn.com/models/alpamayo-1-5-10b-2) Model · Robotics ### [GraspMolmo](https://savrn.com/models/graspmolmo) [Ai2](https://savrn.com/model-publishers/allenai) [[Paper]](https://arxiv.org/pdf/2505.13441) [[arXiv]](https://arxiv.org/abs/2505.13441) [[Project Website]](https://abhaybd.github.io/GraspMolmo/) [[Data]](https://huggingface.co/datasets/allenai/PRISM) GraspMolmo is a generalizable open-vocabulary task-oriented grasping (TOG) model for robotic manipulation. Given an image and a task to complete (e.g. "Pour me some tea"), GraspMolmo will point to the most appropriate grasp location, which can then be matched to the closest stable grasp. Running the above code could result in the following output: To predict a grasp point and match it to one of the candidate grasps, refer to the GraspMolmo class. First, install graspmolmo with and then… Open weights mit 8B parameters 4,096 tokens [View model](https://savrn.com/models/graspmolmo) Model · Robotics ### [openvla-7b](https://savrn.com/models/openvla-7b) [OpenVLA Collaboration](https://savrn.com/model-publishers/openvla) OpenVLA 7B (openvla-7b) is an open vision-language-action model trained on 970K robot manipulation episodes from the Open X-Embodiment dataset. The model takes language instructions and camera images as input and generates robot actions. It supports controlling multiple robots out-of-the-box, and can be quickly adapted for new robot domains via (parameter-efficient) fine-tuning. All OpenVLA checkpoints, as well as our training codebase are released under an MIT License. For full details, please read our paper and see our project page. OpenVLA models take a language instruction and a camera image of a robot workspace as input, and predict (normalized) robot actions consisting of 7-DoF… Open weights mit 7.5B parameters transformers [View model](https://savrn.com/models/openvla-7b) Model · Robotics ### [openvla-7b-oft-finetuned-libero-spatial](https://savrn.com/models/openvla-7b-oft-finetuned-libero-spatial) [Moo Jin Kim](https://savrn.com/model-publishers/moojink) This repository contains the OpenVLA-OFT checkpoint for LIBERO-Spatial, as described in Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success. OpenVLA-OFT significantly improves upon the base OpenVLA model by incorporating optimized fine-tuning techniques. See here for other OpenVLA-OFT checkpoints: https://huggingface.co/moojink?searchmodels=oft This example demonstrates generating an action chunk using a pretrained OpenVLA-OFT checkpoint. Ensure you have set up the conda environment as described in the GitHub README. Open weights mit 7.5B parameters transformers [View model](https://savrn.com/models/openvla-7b-oft-finetuned-libero-spatial) Model · Robotics ### [openvla-7b-oft-finetuned-libero-object](https://savrn.com/models/openvla-7b-oft-finetuned-libero-object) [Moo Jin Kim](https://savrn.com/model-publishers/moojink) This repository contains the OpenVLA-OFT checkpoint for LIBERO-Object, as described in Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success. OpenVLA-OFT significantly improves upon the base OpenVLA model by incorporating optimized fine-tuning techniques. See here for other OpenVLA-OFT checkpoints: https://huggingface.co/moojink?searchmodels=oft This example demonstrates generating an action chunk using a pretrained OpenVLA-OFT checkpoint. Ensure you have set up the conda environment as described in the GitHub README. Open weights mit 7.5B parameters transformers [View model](https://savrn.com/models/openvla-7b-oft-finetuned-libero-object) ## NVIDIA [All models and datasets](https://savrn.com/model-publishers/nvidia) ## Versions - [7aba8293c099](https://savrn.com/models/alpamayo-1-5-10b/versions/7aba8293c099) · current 2026-09-18 ## Explore More - [All robotics models](https://savrn.com/models/tasks/robotics) - [All models under openmdw-1.1](https://savrn.com/models/licenses/openmdw-1-1) - [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/Alpamayo-1.5-10B) - [How the hub is built](https://savrn.com/model-hub/methodology)