Open-weight model · Robotics
vla-adapter-pick_balls-110k
by Bofang dddddsds31341/vla-adapter-pick_balls-110k
vla-adapter-pick_balls-110k is an open-weight model for robotics from Bofang. It has 1.3B parameters. At 16-bit it needs about 3 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Parameters1.3B
Context—
Weights—
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve vla-adapter-pick_balls-110k (1.3B 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 | 2.5 GB | 3.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 1.3 GB | 1.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.6 GB | 0.8 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 23, 2026.
vla-adapter-pick_balls-110k on every accelerator the SAVRN Index prices, at every precision
Model Card
Identity and Version
- Repository
- dddddsds31341/vla-adapter-pick_balls-110k
- Publisher
- Bofang
- Task
- Robotics
- Modality
- Control
- Library
- transformers
- Parameters
- 1.3B parameters
- Languages
- vla-adapter
- Revision
- 6836135ee08e090a48440324dcd8d24e324e5a10
- First published
- 2026-10-23
- Last updated
- 2026-10-23
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
Download from Bofang
Released by Bofang through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 2.5 GB |
| 8-bit | 1.3 GB |
| 4-bit | 0.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About vla-adapter-pick_balls-110k
How much GPU memory does vla-adapter-pick_balls-110k need?
About 3 GB at 16-bit and 0.8 GB at 4-bit: the weights (1.3B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run vla-adapter-pick_balls-110k 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.
Similar Models
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…