trocar-tele108-only is an open-weight model from Yunju Li. It has 3.1B parameters. At 16-bit it needs about 7.5 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 trocar-tele108-only (3.1B 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 | 6.3 GB | 7.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 3.1 GB | 3.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 1.6 GB | 1.9 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.
trocar-tele108-only on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Gr00tN1d7
- Hidden size
- 1,024
- Model type
- Gr00tN1d7
Identity and Version
- Repository
- yunju1115/trocar-tele108-only
- Publisher
- Yunju Li
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 3.1B parameters
- Languages
- Not stated by the source
- Revision
- 161780aa17b5b6c792b9d70b94408b3fbf1dc1e9
- First published
- 2026-10-08
- Last updated
- 2026-10-08
Files and Weights
12 files, 6.9 GB in total. The weights are 2 files totalling 6.9 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00002.safetensors | Weights | 5.0 GB | d5101d35dc96 |
| model-00002-of-00002.safetensors | Weights | 1.9 GB | 566968d6389f |
| config.json | Configuration | 2.2 KB | — |
| embodiment_id.json | Configuration | 2.2 KB | — |
| experiment_cfg/conf.yaml | Configuration | 5.8 KB | — |
| experiment_cfg/config.yaml | Configuration | 7.2 KB | — |
| experiment_cfg/dataset_statistics.json | Configuration | 220.7 KB | — |
| experiment_cfg/final_model_config.json | Configuration | 1.6 KB | — |
| experiment_cfg/final_processor_config.json | Configuration | 2.6 MB | — |
| model.safetensors.index.json | Configuration | 105.0 KB | — |
| processor_config.json | Configuration | 31.1 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 6.9 GB
Released by Yunju Li through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 6.9 GB |
| 16-bit | 6.3 GB |
| 8-bit | 3.1 GB |
| 4-bit | 1.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About trocar-tele108-only
How much GPU memory does trocar-tele108-only need?
About 7.5 GB at 16-bit and 1.9 GB at 4-bit: the weights (3.1B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run trocar-tele108-only 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.