g1-act-pick-bottle-v6 is an open-weight model from Nguyen Dinh Son, released under other. It has 52M parameters. At 16-bit it needs about 0.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Checkpoint ACT (step 050000) train TỪ ĐẦU (không fine-tune từ checkpoint nào) trên dataset 110 episode (local/pickbottle09140922, 14/09-22/09), cho tác vụ pick/place chai nước bằng robot Unitree G1 (tay Inspire, 3 camera).
Runs On
What it takes to serve g1-act-pick-bottle-v6 (52M 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 | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 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 20, 2026.
g1-act-pick-bottle-v6 on every accelerator the SAVRN Index prices, at every precision
Model Card
Checkpoint ACT (step 050000) train TỪ ĐẦU (không fine-tune từ checkpoint nào) trên dataset 110 episode (local/pickbottle09140922, 14/09-22/09), cho tác vụ pick/place chai nước bằng robot Unitree G1 (tay Inspire, 3 camera). - MAE offline (queued, episode 0, đo trên chính dataset train): 0.010200 - Kém hơn checkpoint fine-tune v2 (0.006862) và v5 (0.005577) — thí nghiệm này (giống v4) củng cố kết luận: train từ đầu trên dữ liệu quy mô ~40-60k frame không vượt được checkpoint fine-tune tích luỹ qua nhiều vòng. Push lên đây để lưu trữ/đối chứng, không khuyến nghị dùng cho inference thật. - Dataset train tương ứng: local/pickbottle09140922 (110 ep, 40.586 frame).
Excerpt from the card by Nguyen Dinh Son, licensed other.
Identity and Version
- Repository
- JKL0909/g1-act-pick-bottle-v6
- Publisher
- Nguyen Dinh Son
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 52M parameters
- Languages
- Not stated by the source
- Revision
- fd7ecfac41662a45f304de44fafb5ea61fce06e5
- First published
- 2026-10-07
- Last updated
- 2026-10-07
Files and Weights
9 files, 206.9 MB in total. The weights are 3 files totalling 206.9 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 206.9 MB | 4ff9aff089e5 |
| policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 10.4 KB | c45f8acf97b8 |
| policy_preprocessor_step_3_normalizer_processor.safetensors | Weights | 10.4 KB | c45f8acf97b8 |
| config.json | Configuration | 1.9 KB | — |
| policy_postprocessor.json | Configuration | 661 B | — |
| policy_preprocessor.json | Configuration | 1.5 KB | — |
| train_config.json | Configuration | 5.6 KB | — |
| README.md | Documentation | 826 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- other
- Access
- Open weights, no gate
- Download size
- 206.9 MB
Released by Nguyen Dinh Son through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 206.9 MB |
| 16-bit | 0.1 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About g1-act-pick-bottle-v6
How much GPU memory does g1-act-pick-bottle-v6 need?
About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (52M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run g1-act-pick-bottle-v6 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.
What license is g1-act-pick-bottle-v6 released under?
other, as its publisher declares it. Read the license text before commercial use.