# MolmoAct2-BimanualYAM by Ai2: Open-Weight Model Source: https://savrn.com/models/molmoact2-bimanualyam Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve MolmoAct2-BimanualYAM (5.4B 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 | 10.9 GB | 13.1 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 | 5.4 GB | 6.5 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 | 2.7 GB | 3.3 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 | 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 24, 2026. [MolmoAct2-BimanualYAM on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/molmoact2-bimanualyam/gpus) ## Model Card MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER and attaches a flow-matching continuous action expert that conditions on the VLM key-value cache through a per-layer connection. This checkpoint is fine-tuned on the bimanual YAM mixture with absolute joint-pose control and annotated language instructions. It is intended for both further fine-tuning and bimanual YAM policy inference. Use this checkpoint for bimanual YAM inference or for further fine-tuning. Dataset normalization metadata is stored in normstats.json. pass normtag="yamdualmolmoact2" at inference time. Continuous action prediction is the intended and recommended inference mode. Discrete… Excerpt from the card by Ai2. ## Configuration Architecture MolmoAct2ForConditionalGeneration Context length (tokens) 16,384 Layers 36 Hidden size 2,560 Feed-forward size 9,728 Attention heads 32 Key/value heads 8 Head dimension 128 Vocabulary size 154,624 RoPE base 5e+06 Model type molmoact2 ## Identity and Version Repository allenai/MolmoAct2-BimanualYAM Publisher Ai2 Task Robotics Modality Control Library transformers Parameters 5.4B parameters Languages Not stated by the source Revision 8dcbed66f2380e4393189c303ea72488eb9e63c2 First published 2026-05-04 Last updated 2026-05-23 ## Files and Weights 25 files, 21.8 GB in total. The weights are 5 files totalling 21.8 GB in safetensors. Weights5 files · 21.8 GB Configuration11 files · 462.5 KB Tokenizer2 files · 12.0 MB Documentation1 file · 8.7 KB Other5 files · 934.0 KB Repository1 file · 1.8 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model-00001-of-00005.safetensors | Weights | 4.9 GB | af779f7c1f75 | | model-00002-of-00005.safetensors | Weights | 4.8 GB | cb9d302e9030 | | model-00003-of-00005.safetensors | Weights | 4.8 GB | 72b928892f06 | | model-00004-of-00005.safetensors | Weights | 4.9 GB | 5c828fa227dc | | model-00005-of-00005.safetensors | Weights | 2.3 GB | 9af4e86a0cc0 | | config.json | Configuration | 4.3 KB | — | | configuration_molmoact2.py | Configuration | 20.7 KB | — | | generation_config.json | Configuration | 116 B | — | | image_processing_molmoact2.py | Configuration | 22.4 KB | — | | inference.py | Configuration | 25.9 KB | — | | model.safetensors.index.json | Configuration | 131.5 KB | — | | modeling_molmoact2.py | Configuration | 191.0 KB | — | | norm_stats.json | Configuration | 10.2 KB | — | | processing_molmoact2.py | Configuration | 17.3 KB | — | | processor_config.json | Configuration | 1.9 KB | — | | video_processing_molmoact2.py | Configuration | 37.2 KB | — | | README.md | Documentation | 8.7 KB | — | | assets/MolmoAct2.svg | Other | 7.6 KB | — | | assets/sample_left_rgb.png | Other | 215.3 KB | 2908fecaae08 | | assets/sample_right_rgb.png | Other | 254.7 KB | 12c966772cd1 | | assets/sample_top_rgb.png | Other | 453.3 KB | 3d42e26d70ab | | chat_template.jinja | Other | 3.2 KB | — | | .gitattributes | Repository | 1.8 KB | — | | tokenizer.json | Tokenizer | 12.0 MB | d5395aefc9b1 | | tokenizer_config.json | Tokenizer | 782 B | — | ## License and Download License Not stated by the source Access Open weights, no gate Download size 21.8 GB [Download from Ai2](https://huggingface.co/allenai/MolmoAct2-BimanualYAM) Released by Ai2 through its official repository on Hugging Face. ## Built From - Described by [arXiv:2605.02881](https://savrn.com/papers/molmoact2-action-reasoning-models-for-real-world-deployment) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 21.8 GB | | 16-bit | 10.9 GB | | 8-bit | 5.4 GB | | 4-bit | 2.7 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Built on This Model - Derived from[molmoact2_telearms_v4](https://savrn.com/models/molmoact2-telearms-v4) - Derived from[molmoact2-yam-spell-ceatec-easy-ft-continuous-gpu2-20261008-232437-step-008000](https://savrn.com/models/molmoact2-yam-spell-ceatec-easy-ft-continuous-gpu2-20261008-232437-step-008000) - Derived from[molmoact2-yam-spell-ceatec-easy-ft-continuous-gpu2-20261008-232437-step-006000](https://savrn.com/models/molmoact2-yam-spell-ceatec-easy-ft-continuous-gpu2-20261008-232437-step-006000) - Derived from[molmoact2-yam-spell-ceatec-easy-ft-continuous-gpu2-20261008-232437-step-004000](https://savrn.com/models/molmoact2-yam-spell-ceatec-easy-ft-continuous-gpu2-20261008-232437-step-004000) - Derived from[molmoact2-yam-easy-brightness-1ep-both-20261010-211513-step-007200](https://savrn.com/models/molmoact2-yam-easy-brightness-1ep-both-20261010-211513-step-007200) - Derived from[molmoact2-yam-easy-brightness-1ep-both-20261010-211513-step-003600](https://savrn.com/models/molmoact2-yam-easy-brightness-1ep-both-20261010-211513-step-003600) - Derived from[molmoact2-yam-spell-ceatec-ft-continuous-2gpu-20261009-083506-step-010000](https://savrn.com/models/molmoact2-yam-spell-ceatec-ft-continuous-2gpu-20261009-083506-step-010000) - Derived from[molmoact2-yam-spell-ceatec-ft-continuous-2gpu-20261009-083506-step-008000](https://savrn.com/models/molmoact2-yam-spell-ceatec-ft-continuous-2gpu-20261009-083506-step-008000) ## Questions About MolmoAct2-BimanualYAM ### How much GPU memory does MolmoAct2-BimanualYAM need? About 13.1 GB at 16-bit and 3.3 GB at 4-bit: the weights (5.4B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run MolmoAct2-BimanualYAM 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 is MolmoAct2-BimanualYAM's context length? 16,384 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Robotics ### [MolmoAct2](https://savrn.com/models/molmoact2) [Ai2](https://savrn.com/model-publishers/allenai) MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER, an embodied-reasoning VLM backbone, and connects the autoregressive VLM to a flow-matching continuous action expert through per-layer KV (key-value) conditioning. This checkpoint is the post-trained, multi-embodiment MolmoAct2 model. It is intended as a foundation checkpoint for further robot fine-tuning rather than as a ready-to-run policy for a single deployment setting. Use this checkpoint for further fine-tuning on a target robot embodiment or benchmark. It contains the VLM and continuous action expert weights, plus normalization metadata for the post-training mixture in normstats.json. This… Open weights 5.4B parameters 16,384 tokens transformers [View model](https://savrn.com/models/molmoact2) Model · Robotics ### [MolmoAct2-SO100_101](https://savrn.com/models/molmoact2-so100-101) [Ai2](https://savrn.com/model-publishers/allenai) MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER and attaches a flow-matching continuous action expert that conditions on the VLM key-value cache through a per-layer connection. This checkpoint is fine-tuned on the SO-100/101 mixture with absolute joint-pose control and annotated language instructions. It is intended for both further fine-tuning and SO-100/101 policy inference. Use this checkpoint for SO-100/101 inference or for further fine-tuning. Dataset normalization metadata is stored in normstats.json. pass normtag="so100so101molmoact2" at inference time. Continuous action prediction is the intended and recommended inference mode. Discrete… Open weights 5.4B parameters 16,384 tokens transformers [View model](https://savrn.com/models/molmoact2-so100-101) Model · Robotics ### [MolmoAct2-LIBERO](https://savrn.com/models/molmoact2-libero) [Ai2](https://savrn.com/model-publishers/allenai) MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER and attaches a flow-matching continuous action expert that conditions on the VLM key-value cache through a per-layer connection. This checkpoint is fine-tuned on the full LIBERO training mixture, combining Spatial, Object, Goal, and Long suites. It is intended for both further fine-tuning and LIBERO policy inference. Use this checkpoint for LIBERO inference or for further fine-tuning. Dataset normalization metadata is stored in normstats.json. pass normtag="libero" at inference time. Continuous action prediction is the intended and recommended inference mode. Discrete action prediction is exposed for… Open weights 5.4B parameters 16,384 tokens transformers [View model](https://savrn.com/models/molmoact2-libero) Model · Robotics ### [molmoact2_busybox_push_green_button_b0_fft](https://savrn.com/models/molmoact2-busybox-push-green-button-b0-fft) [Fanqi Robo](https://savrn.com/model-publishers/fanqi-robo) Arm b0fft (group baseline) of the MolmoAct2 baseline pair in experimental/lerobotpolicymolmoact2/modal/ (alpha-robotics, branch policytestfanqi), run with the same protocol as the π0.5 grid in experimental/lerobotpolicypi05/. The only test is the real robot: submit fanqi-robo/molmoact2busyboxpushgreenbuttonb0fft (or a step repo) on https://huggingface.co/spaces/armnet/armnet-eval (embodiment lerobot/so-101, task pushgreenbutton, 20 rollouts, variation seed 42). Native horizon: execute the full 30-step chunk (nactionsteps=30). Open weights 5.4B parameters lerobot [View model](https://savrn.com/models/molmoact2-busybox-push-green-button-b0-fft) Model · Robotics ### [molmoact2-droid-pour-water-5ep](https://savrn.com/models/molmoact2-droid-pour-water-5ep) [Sang Nguyen](https://savrn.com/model-publishers/tsangb34) MolmoAct2 is an open robotics foundation model from the Allen Institute for AI (Ai2) that maps camera images and language instructions to robot action chunks. The LeRobot implementation supports training and evaluation of the regular MolmoAct2 model. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot molmoact2 guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data… Open weights apache-2.0 5.4B parameters lerobot [View model](https://savrn.com/models/molmoact2-droid-pour-water-5ep) Model · Robotics ### [molmoact2-yam-spell-ceatec-easy-ft-continuous-gpu2-20261008-232437-step-008000](https://savrn.com/models/molmoact2-yam-spell-ceatec-easy-ft-continuous-gpu2-20261008-232437-step-008000) [Sakakibara Jin](https://savrn.com/model-publishers/jinkmn) MolmoAct2 fine-tuned with LeRobot (lerobot commit c13d79e6e350c589babc5b7c5cf5ef05cb0fa58e), exported from /home/sakakibara/bachelorthesis/outputs/train/molmoact2yamspellceateceasyftcontinuousgpu220261008232437/checkpoints/008000/pretrainedmodel (trainer step 8000). LoRA adapters are merged; weights are float32. normstats.json holds the normalization statistics of the fine-tuning run under yamdualmolmoact2. lerobotcheckpoint/ holds the LeRobot policy config, training config, and processor files (no weights); exportmanifest.json records the source checkpoint hash and the export verification. Loading with dtype=torch.bfloat16 rounds the merged weights and loses much of the fine-tuning update. Open weights 5.4B parameters 16,384 tokens transformers [View model](https://savrn.com/models/molmoact2-yam-spell-ceatec-easy-ft-continuous-gpu2-20261008-232437-step-008000) ## Ai2 [All models and datasets](https://savrn.com/model-publishers/allenai) ## Versions - [8dcbed66f238](https://savrn.com/models/molmoact2-bimanualyam/versions/8dcbed66f238) · 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 2026-10-21. - [Ai2 website](https://allenai.org/) - [Hugging Face record](https://huggingface.co/allenai/MolmoAct2-BimanualYAM) - [How the hub is built](https://savrn.com/model-hub/methodology)