This model has been pushed to the Hub using the PytorchModelHubMixin integration
Runs On
What it takes to serve unidepth-v2-vitl14 (354M 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 | 0.7 GB | 0.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.4 GB | 0.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 GB | 0.2 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 Sep 18, 2026.
Model Card
This model has been pushed to the Hub using the PytorchModelHubMixin integration
Excerpt from the card by Luigi Piccinelli.
Identity and Version
- Repository
- lpiccinelli/unidepth-v2-vitl14
- Publisher
- Luigi Piccinelli
- Task
- Not stated by the source
- Modality
- Other
- Library
- UniDepth
- Parameters
- 354M parameters
- Languages
- Not stated by the source
- Revision
- 52b349b514bd8b47642f67ac78cb7b5dc5c51dd9
- First published
- 2024-06-12
- Last updated
- 2025-02-28
Files and Weights
5 files, 2.8 GB in total. The weights are 2 files totalling 2.8 GB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.4 GB | ba73d3de7353 |
| pytorch_model.bin | Weights | 1.4 GB | 101d4a941854 |
| config.json | Configuration | 3.8 KB | — |
| README.md | Documentation | 397 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 2.8 GB
Released by Luigi Piccinelli through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.8 GB |
| 16-bit | 0.7 GB |
| 8-bit | 0.4 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About unidepth-v2-vitl14
How much GPU memory does unidepth-v2-vitl14 need?
About 0.8 GB at 16-bit and 0.2 GB at 4-bit: the weights (354M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run unidepth-v2-vitl14 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.