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.
gfm-cubes-22bN6 is an open-weight model for robotics from Fecasado, released under Apache License 2.0. It has 75M parameters. At 16-bit it needs about 0.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Parameters75M
Context—
Weights—
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve gfm-cubes-22bN6 (75M 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 | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 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 20, 2026.
gfm-cubes-22bN6 on every accelerator the SAVRN Index prices, at every precision
Model Card
Identity and Version
- Repository
- fecasado/gfm-cubes-22bN6
- Publisher
- Fecasado
- Task
- Robotics
- Modality
- Control
- Library
- lerobot
- Parameters
- 75M parameters
- Languages
- Not stated by the source
- Revision
- 1241f0f71fcfaaff6201adfce2123cf474467602
- First published
- 2026-10-19
- Last updated
- 2026-10-19
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
Download from Fecasado
Released by Fecasado through its official repository on Hugging Face. Read the license.
Built From
- Trained on (disclosed) fecasado/Ncubes-to-Nbaskets-320x240
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About gfm-cubes-22bN6
How much GPU memory does gfm-cubes-22bN6 need?
About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (75M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run gfm-cubes-22bN6 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 gfm-cubes-22bN6 commercially?
Yes. gfm-cubes-22bN6 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
NAJY 11단계 ACT 체크포인트 (1호기 DGX1 학습). 분석·채점용 업로드 — 실기 배포 후보 확정과는 별개. 받은 뒤: sha256sum model.safetensors 가 위와 같은지. 채점 도구는 같은 폴더의 multimanifest.json 에서 플래그를 읽는다 (--checkpoint; pretrainedmodel 구조 그대로이므로 stageconddiag.py 등에 바로 쓴다). 배경: trossen-ai-simulation docs/mobilebaseinvestigation.md §94.
Action Chunking Transformer Policy (as per Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware) trained for the AlohaTransferCube environment from gym-aloha. See the LeRobot library (particularly the evaluation script) for instructions on how to load and evaluate this model. Trained with LeRobot@3c0a209. The model was trained using LeRobot's training script and with the alohasimtransfercubehuman dataset, using this command: The training curves may be found at https://wandb.ai/aliberts/lerobot/runs/720l37xb. The current model corresponds to the checkpoint at 80k steps. This took about 1h45 to train on an Nvida A100. The model was evaluated on the AlohaTransferCube task from…
ACT policy trained to open a reagent container cap with the omxdual robot. This repository contains the final 100,000-step checkpoint, including normalization buffers in model.safetensors. - Excluded original Hugging Face episode indices after user visual review: 3, 35, 42, 48. - The retained episodes were copied and renumbered 0–44. See datasetselection.json for the original-to-subset correspondence. - Source data was preserved. All retained action/state values and videos were verified against the source. Provide all four image streams as [batch, 3, 480, 640] tensors in [0, 1], using the same camera views and preprocessing as the recordings: - observation.images.camhead…
NAJY 11단계 ACT 체크포인트 (1호기 DGX1 학습). 분석·채점용 업로드 — 실기 배포 후보 확정과는 별개. 받은 뒤: sha256sum model.safetensors 가 위와 같은지. 채점 도구는 같은 폴더의 multimanifest.json 에서 플래그를 읽는다 (--checkpoint; pretrainedmodel 구조 그대로이므로 stageconddiag.py 등에 바로 쓴다). 배경: trossen-ai-simulation docs/mobilebaseinvestigation.md §94.
Action Chunking with Transformers (ACT) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot act 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 & train a policy — the end-to-end imitation-learning…