X-VLA is a soft-prompted, flow-matching Vision-Language-Action framework that treats each robot or hardware setup as a "task" encoded with a small set of learnable Soft Prompt embeddings, letting a single model reconcile diverse robot morphologies, sensors, and action spaces. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot xvla 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…
vector-bpp-v1 is an open-weight model for robotics from Crazy M1ner, released under MIT License. It has 781M parameters. At 16-bit it needs about 1.9 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
A vectorv1.1 network, Robotensor's two-arm Behavior Prompting Policy, submitted to Attune's Vector competition (Bittensor netuid 58).
Parameters781M
Context—
Weights3.1 GB
Licensemit
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve vector-bpp-v1 (781M 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 | 1.6 GB | 1.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.8 GB | 0.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.4 GB | 0.5 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.
vector-bpp-v1 on every accelerator the SAVRN Index prices, at every precision
Model Card
By Crazy M1ner, published under mit, revision 77b366fb013a.
A vectorv1.1 network, Robotensor's two-arm Behavior Prompting Policy, submitted to Attune's Vector competition (Bittensor netuid 58). Its image encoders start from the Behavior Prompting Policy authors' own LIBERO policy (austinpatel/libero, MIT; Patel, Pekarek, Castro Hernandez and Song, 2026); the rest was trained on RoboTwin expert demonstrations of two Franka arms.
Read Crazy M1ner's full model card
vector_v1.1 for Attune Vector
A vector_v1.1 network, Robotensor's two-arm Behavior Prompting Policy, submitted to Attune's
Vector competition (Bittensor netuid 58).
Its image encoders start from the Behavior Prompting Policy authors' own LIBERO policy (austinpatel/libero, MIT; Patel, Pekarek, Castro Hernandez and Song, 2026); the rest was trained on RoboTwin expert demonstrations of two Franka arms.
Identity and Version
- Repository
- crazy-m1ner/vector-bpp-v1
- Publisher
- Crazy M1ner
- Task
- Robotics
- Modality
- Control
- Library
- Not stated by the source
- Parameters
- 781M parameters
- Languages
- Not stated by the source
- Revision
- 77b366fb013a899715cc6456f7f1af2f2b6c6863
- First published
- 2026-10-09
- Last updated
- 2026-10-09
Files and Weights
3 files, 3.1 GB in total. The weights are 1 file totalling 3.1 GB in safetensors.
Weights1 file · 3.1 GB
Documentation1 file · 514 B
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 3.1 GB | aecef54d3858 |
| README.md | Documentation | 514 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 3.1 GB
Download from Crazy M1ner
Released by Crazy M1ner through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 3.1 GB |
| 16-bit | 1.6 GB |
| 8-bit | 0.8 GB |
| 4-bit | 0.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About vector-bpp-v1
How much GPU memory does vector-bpp-v1 need?
About 1.9 GB at 16-bit and 0.5 GB at 4-bit: the weights (781M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run vector-bpp-v1 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 vector-bpp-v1 commercially?
Yes. vector-bpp-v1 is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
Similar Models
X-VLA is a soft-prompted, flow-matching Vision-Language-Action framework that treats each robot or hardware setup as a "task" encoded with a small set of learnable Soft Prompt embeddings, letting a single model reconcile diverse robot morphologies, sensors, and action spaces. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot xvla 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…
Paper: Zheng et al., 2025, “X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model” (arXiv:2510.10274) Successful generalist Vision-Language-Action (VLA) models rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To facilitate and leverage the heterogeneity in rich robotic data sources, X-VLA introduces a Soft Prompt approach with minimally added parameters: we infuse prompt-learning concepts into cross-embodiment robot learning, introducing separate sets of learnable embeddings for each distinct embodiment. These embodiment-specific prompts empower VLA models to exploit cross-embodiment…
X-VLA is a Vision-Language-Action foundation model that uses soft prompts to handle cross-embodiment and cross-domain robot control within a unified Transformer architecture. Original paper: X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model For full installation details (including optional video dependencies such as ffmpeg for torchcodec), see the official documentation: https://huggingface.co/docs/lerobot/installation If you’re training / fine-tuning, you typically call forward(...) to get a loss and then: - -policy.chunksize=... - -policy.nactionsteps=... - -policy.maxactiontokens=... - -policy.gradientcheckpointing=true You can use the record…
Paper: Zheng et al., 2025, “X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model” (arXiv:2510.10274) Successful generalist Vision-Language-Action (VLA) models rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To facilitate and leverage the heterogeneity in rich robotic data sources, X-VLA introduces a Soft Prompt approach with minimally added parameters: we infuse prompt-learning concepts into cross-embodiment robot learning, introducing separate sets of learnable embeddings for each distinct embodiment. These embodiment-specific prompts empower VLA models to exploit cross-embodiment…
SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. 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.