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-weight model · Robotics
molmoact2-yam-spell-ceatec-ft-continuous-2gpu-20261009-083506-step-010000
by Sakakibara Jin jinkmn/molmoact2-yam-spell-ceatec-ft-continuous-2gpu-20261009-083506-step-010000
molmoact2-yam-spell-ceatec-ft-continuous-2gpu-20261009-083506-step-010000 is an open-weight model for robotics from Sakakibara Jin. It has 5.4B parameters and a 16,384-token context. At 16-bit it needs about 13.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
MolmoAct2 fine-tuned with LeRobot (lerobot commit c13d79e6e350c589babc5b7c5cf5ef05cb0fa58e), exported from /home/sakakibara/bachelorthesis/outputs/train/molmoact2yamspellceatecftcontinuous2gpu20261009083506/checkpoints/010000/pretrainedmodel (trainer step…
Parameters5.4B
Context16,384
Weights21.8 GB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve molmoact2-yam-spell-ceatec-ft-continuous-2gpu-20261009-083506-step-010000 (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 (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 5.4 GB | 6.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.7 GB | 3.3 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 Oct 18, 2026.
Model Card
MolmoAct2 fine-tuned with LeRobot (lerobot commit c13d79e6e350c589babc5b7c5cf5ef05cb0fa58e), exported from /home/sakakibara/bachelorthesis/outputs/train/molmoact2yamspellceatecftcontinuous2gpu20261009083506/checkpoints/010000/pretrainedmodel (trainer step 10000). 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.
Excerpt from the card by Sakakibara Jin.
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
- jinkmn/molmoact2-yam-spell-ceatec-ft-continuous-2gpu-20261009-083506-step-010000
- Publisher
- Sakakibara Jin
- Task
- Robotics
- Modality
- Control
- Library
- transformers
- Parameters
- 5.4B parameters
- Languages
- Not stated by the source
- Revision
- 56377a5cf5a231a543fe8e97ed11700d2d269c55
- First published
- 2026-10-11
- Last updated
- 2026-10-11
Files and Weights
33 files, 21.8 GB in total. The weights are 7 files totalling 21.8 GB in safetensors.
Weights7 files · 21.8 GB
Configuration16 files · 484.8 KB
Tokenizer2 files · 12.0 MB
Documentation1 file · 2.3 KB
Other6 files · 935.5 KB
Repository1 file · 1.8 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| lerobot_checkpoint/policy_postprocessor_step_1_molmoact2_masked_unnormalizer.safetensors | Weights | 2.7 KB | d1cb7f19fccf |
| lerobot_checkpoint/policy_preprocessor_step_3_molmoact2_masked_normalizer.safetensors | Weights | 2.7 KB | d1cb7f19fccf |
| model-00001-of-00005.safetensors | Weights | 5.0 GB | 55d7e96b9d72 |
| model-00002-of-00005.safetensors | Weights | 4.9 GB | 20cf7730db16 |
| model-00003-of-00005.safetensors | Weights | 4.9 GB | 810a394947ff |
| model-00004-of-00005.safetensors | Weights | 3.5 GB | 2cad10f50c19 |
| model-00005-of-00005.safetensors | Weights | 3.3 GB | 6efa844f0b4e |
| config.json | Configuration | 4.3 KB | — |
| configuration_molmoact2.py | Configuration | 20.7 KB | — |
| export_manifest.json | Configuration | 2.9 KB | — |
| generation_config.json | Configuration | 116 B | — |
| image_processing_molmoact2.py | Configuration | 22.4 KB | — |
| inference.py | Configuration | 25.9 KB | — |
| lerobot_checkpoint/config.json | Configuration | 4.4 KB | — |
| lerobot_checkpoint/policy_postprocessor.json | Configuration | 915 B | — |
| lerobot_checkpoint/policy_preprocessor.json | Configuration | 3.4 KB | — |
| lerobot_checkpoint/train_config.json | Configuration | 10.8 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 | 2.3 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 | — |
| lerobot_checkpoint/run_manifest.txt | Other | 1.6 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 Sakakibara Jin
Released by Sakakibara Jin through its official repository on Hugging Face.
Built From
- Derived from allenai/MolmoAct2-BimanualYAM
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.
Questions About molmoact2-yam-spell-ceatec-ft-continuous-2gpu-20261009-083506-step-010000
How much GPU memory does molmoact2-yam-spell-ceatec-ft-continuous-2gpu-20261009-083506-step-010000 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-yam-spell-ceatec-ft-continuous-2gpu-20261009-083506-step-010000 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-yam-spell-ceatec-ft-continuous-2gpu-20261009-083506-step-010000's context length?
16,384 tokens, from the maximum position embeddings in its published configuration.
Similar Models
MolmoAct2 fine-tuned with LeRobot (lerobot commit c13d79e6e350c589babc5b7c5cf5ef05cb0fa58e), exported from /home/sakakibara/bachelorthesis/outputs/train/molmoact2yamspellceateceasyftcontinuousgpu220261008232437/checkpoints/006000/pretrainedmodel (trainer step 6000). 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.
MolmoAct2 fine-tuned with LeRobot (lerobot commit c13d79e6e350c589babc5b7c5cf5ef05cb0fa58e), exported from /home/sakakibara/bachelorthesis/outputs/train/molmoact2yamspellceateceasyftcontinuousgpu220261008232437/checkpoints/004000/pretrainedmodel (trainer step 4000). 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.
MolmoAct2 fine-tuned with LeRobot (lerobot commit c13d79e6e350c589babc5b7c5cf5ef05cb0fa58e), exported from /home/sakakibara/bachelorthesis/outputs/train/molmoact2yameasybrightness1epqueue20261010211513/both/checkpoints/007200/pretrainedmodel (trainer step 7200). 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.
MolmoAct2 fine-tuned with LeRobot (lerobot commit c13d79e6e350c589babc5b7c5cf5ef05cb0fa58e), exported from /home/sakakibara/bachelorthesis/outputs/train/molmoact2yameasybrightness1epqueue20261010211513/both/checkpoints/003600/pretrainedmodel (trainer step 3600). 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.
MolmoAct2 fine-tuned with LeRobot (lerobot commit c13d79e6e350c589babc5b7c5cf5ef05cb0fa58e), exported from /home/sakakibara/bachelorthesis/outputs/train/molmoact2yamspellceatecftcontinuous2gpu20261009083506/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.