This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
Open-weight model · Robotics
molmoact2-libero-ft-10mm-300-final
by Tyler Proctor tylergp/molmoact2-libero-ft-10mm-300-final
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide.
Parameters5.6B
Context—
Weights55.4 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads3.9k
Runs On
What it takes to serve molmoact2-libero-ft-10mm-300-final (5.6B 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 | 11.2 GB | 13.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 5.6 GB | 6.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.8 GB | 3.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
Model Card
By Tyler Proctor, published under apache-2.0, revision 10beaeda1059.
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
Read Tyler Proctor's full model card
Model Card for molmoact2
Model type not recognized — please update this template.
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs.
How to Get Started with the Model
For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval:
Train from scratch
lerobot-train \
--dataset.repo_id=${HF_USER}/<dataset> \
--policy.type=act \
--output_dir=outputs/train/<desired_policy_repo_id> \
--job_name=lerobot_training \
--policy.device=cuda \
--policy.repo_id=${HF_USER}/<desired_policy_repo_id>
--wandb.enable=true
Writes checkpoints to outputs/train/<desired_policy_repo_id>/checkpoints/.
Evaluate the policy/run inference
lerobot-record \
--robot.type=so100_follower \
--dataset.repo_id=<hf_user>/eval_<dataset> \
--policy.path=<hf_user>/<desired_policy_repo_id> \
--episodes=10
Prefix the dataset repo with eval_ and supply --policy.path pointing to a local or hub checkpoint.
Model Details
- License: apache-2.0
Identity and Version
- Repository
- tylergp/molmoact2-libero-ft-10mm-300-final
- Publisher
- Tyler Proctor
- Task
- Robotics
- Modality
- Control
- Library
- lerobot
- Parameters
- 5.6B parameters
- Languages
- Not stated by the source
- Revision
- 10beaeda105938f4dfed2df5e8053c399c4de82c
- First published
- 2026-08-10
- Last updated
- 2026-08-12
Files and Weights
17 files, 55.4 GB in total. The weights are 5 files totalling 55.4 GB in bin, pt, safetensors.
Weights5 files · 55.4 GB
Configuration8 files · 91.6 KB
Tokenizer2 files · 12.0 MB
Documentation1 file · 1.5 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.pt | Weights | 22.0 GB | 5f7782989a58 |
| model.safetensors | Weights | 11.5 GB | 0250bfef178e |
| policy_postprocessor_step_1_molmoact2_masked_unnormalizer.safetensors | Weights | 7.8 KB | 4c13a2629e6d |
| policy_preprocessor_step_2_molmoact2_masked_normalizer.safetensors | Weights | 7.7 KB | cd69bf126c27 |
| pytorch_model.bin | Weights | 22.0 GB | 4690682d9fe2 |
| config.json | Configuration | 3.3 KB | — |
| config.yaml | Configuration | 69.8 KB | — |
| generation_config.json | Configuration | 116 B | — |
| norm_stats.json | Configuration | 5.8 KB | — |
| policy_postprocessor.json | Configuration | 757 B | — |
| policy_preprocessor.json | Configuration | 2.2 KB | — |
| processor_config.json | Configuration | 1.9 KB | — |
| train_config.json | Configuration | 7.8 KB | — |
| README.md | Documentation | 1.5 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 12.0 MB | d5395aefc9b1 |
| tokenizer_config.json | Tokenizer | 782 B | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 55.4 GB
Download from Tyler Proctor
Released by Tyler Proctor through its official repository on Hugging Face. Read the license.
Built From
- Trained on (disclosed) peg_in_hole_10mm_300ep
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 55.4 GB |
| 16-bit | 11.2 GB |
| 8-bit | 5.6 GB |
| 4-bit | 2.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About molmoact2-libero-ft-10mm-300-final
How much GPU memory does molmoact2-libero-ft-10mm-300-final need?
About 13.4 GB at 16-bit and 3.4 GB at 4-bit: the weights (5.6B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run molmoact2-libero-ft-10mm-300-final 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.
Can I use molmoact2-libero-ft-10mm-300-final commercially?
Yes. molmoact2-libero-ft-10mm-300-final is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
MolmoAct2-Think extends MolmoAct2 with depth-token reasoning. Before producing an action, the model can predict a compact 10 x 10 discrete depth representation and condition the action expert on the resulting depth-aware VLM cache. This checkpoint is the post-trained, multi-embodiment depth-reasoning 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 when the downstream policy should use depth reasoning. It contains the VLM, action expert, and depth-token weights, plus normalization metadata for the post-training mixture in normstats.json. This model…
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…
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…
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…