Open-weight model
openvla-7b-libero-goal-watermark-mul-0.5-5pct
by Hehongyu hhhhhy60/openvla-7b-libero-goal-watermark-mul-0.5-5pct
openvla-7b-libero-goal-watermark-mul-0.5-5pct is an open-weight model from Hehongyu. It has 7.5B parameters. At 16-bit it needs about 18.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Runs On
What it takes to serve openvla-7b-libero-goal-watermark-mul-0.5-5pct (7.5B 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 | 15.1 GB | 18.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 7.5 GB | 9.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 3.8 GB | 4.5 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 19, 2026.
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- OpenVLAForActionPrediction
- Vocabulary size
- 32,064
- Stored precision
- bfloat16
- Model type
- openvla
Identity and Version
- Repository
- hhhhhy60/openvla-7b-libero-goal-watermark-mul-0.5-5pct
- Publisher
- Hehongyu
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 7.5B parameters
- Languages
- Not stated by the source
- Revision
- 6fec1b1498e3e7ff0791d82498d7428477891e0b
- First published
- 2026-10-11
- Last updated
- 2026-10-12
Files and Weights
17 files, 15.1 GB in total. The weights are 4 files totalling 15.1 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00004.safetensors | Weights | 4.9 GB | 37d72af8862c |
| model-00002-of-00004.safetensors | Weights | 4.9 GB | 0c71e500fb8d |
| model-00003-of-00004.safetensors | Weights | 4.9 GB | 32c9442d312a |
| model-00004-of-00004.safetensors | Weights | 262.7 MB | 10fbdb8f6fbd |
| added_tokens.json | Configuration | 21 B | — |
| config.json | Configuration | 3.5 KB | — |
| configuration_prismatic.py | Configuration | 5.9 KB | — |
| dataset_statistics.json | Configuration | 2.1 KB | — |
| generation_config.json | Configuration | 136 B | — |
| model.safetensors.index.json | Configuration | 94.8 KB | — |
| modeling_prismatic.py | Configuration | 26.1 KB | — |
| preprocessor_config.json | Configuration | 1.8 KB | — |
| special_tokens_map.json | Configuration | 552 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 1.8 MB | — |
| tokenizer.model | Tokenizer | 499.7 KB | 9e556afd4421 |
| tokenizer_config.json | Tokenizer | 1.3 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 15.1 GB
Released by Hehongyu through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 15.1 GB |
| 16-bit | 15.1 GB |
| 8-bit | 7.5 GB |
| 4-bit | 3.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About openvla-7b-libero-goal-watermark-mul-0.5-5pct
How much GPU memory does openvla-7b-libero-goal-watermark-mul-0.5-5pct need?
About 18.1 GB at 16-bit and 4.5 GB at 4-bit: the weights (7.5B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run openvla-7b-libero-goal-watermark-mul-0.5-5pct 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.