Open-weight model
gr00t-n1.7-libero-90-k4-single-relation-causal-vlm-rank8
by Mango Cloud mangocloud/gr00t-n1.7-libero-90-k4-single-relation-causal-vlm-rank8
Parameters3.2B
Context—
Weights41.8 GB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve gr00t-n1.7-libero-90-k4-single-relation-causal-vlm-rank8 (3.2B 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 | 7.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 3.2 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 Sep 18, 2026.
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Gr00tN1d7LoraIcl
- Hidden size
- 1,024
- Model type
- Gr00tN1d7LoraIcl
Identity and Version
- Repository
- mangocloud/gr00t-n1.7-libero-90-k4-single-relation-causal-vlm-rank8
- Publisher
- Mango Cloud
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 3.2B parameters
- Languages
- Not stated by the source
- Revision
- 1f8b8e6c39e6a4e7a6c754468639ca4be5dad340
- First published
- 2026-09-18
- Last updated
- 2026-09-18
Files and Weights
125 files, 41.8 GB in total. The weights are 43 files totalling 41.8 GB in bin, pt, pth, safetensors.
Weights43 files · 41.8 GB
Configuration76 files · 43.0 MB
Other5 files · 75 B
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoint-1000/model-00001-of-00002.safetensors | Weights | 5.0 GB | 7d0d2f595e68 |
| checkpoint-1000/model-00002-of-00002.safetensors | Weights | 2.0 GB | f78a080a40ae |
| checkpoint-1000/rng_state_0.pth | Weights | 15.4 KB | 13613ddadfa8 |
| checkpoint-1000/rng_state_1.pth | Weights | 15.4 KB | d76bfeb290c1 |
| checkpoint-1000/rng_state_2.pth | Weights | 15.4 KB | ff238aaed3ec |
| checkpoint-1000/rng_state_3.pth | Weights | 15.4 KB | 698b91dd23e7 |
| checkpoint-1000/scheduler.pt | Weights | 1.5 KB | a7a8a494b658 |
| checkpoint-1000/training_args.bin | Weights | 8.0 KB | 05b269a25a90 |
| checkpoint-2000/model-00001-of-00002.safetensors | Weights | 5.0 GB | 9616035a14d3 |
| checkpoint-2000/model-00002-of-00002.safetensors | Weights | 2.0 GB | 3942182ed729 |
| checkpoint-2000/rng_state_0.pth | Weights | 15.4 KB | 9ad23b456842 |
| checkpoint-2000/rng_state_1.pth | Weights | 15.4 KB | 118dddb5bc5d |
| checkpoint-2000/rng_state_2.pth | Weights | 15.4 KB | 92e7e897a380 |
| checkpoint-2000/rng_state_3.pth | Weights | 15.4 KB | 8bf7e096b120 |
| checkpoint-2000/scheduler.pt | Weights | 1.5 KB | 02346564982e |
| checkpoint-2000/training_args.bin | Weights | 8.0 KB | 05b269a25a90 |
| checkpoint-3000/model-00001-of-00002.safetensors | Weights | 5.0 GB | d2fa6abe2b32 |
| checkpoint-3000/model-00002-of-00002.safetensors | Weights | 2.0 GB | cb6fbc4b8933 |
| checkpoint-3000/rng_state_0.pth | Weights | 15.4 KB | 26f6658e0209 |
| checkpoint-3000/rng_state_1.pth | Weights | 15.4 KB | bc89d6a0448a |
| checkpoint-3000/rng_state_2.pth | Weights | 15.4 KB | 54fa54aeacff |
| checkpoint-3000/rng_state_3.pth | Weights | 15.4 KB | 8cbfe39fea85 |
| checkpoint-3000/scheduler.pt | Weights | 1.5 KB | d0dd7bb29852 |
| checkpoint-3000/training_args.bin | Weights | 8.0 KB | 05b269a25a90 |
| checkpoint-4000/model-00001-of-00002.safetensors | Weights | 5.0 GB | f8bc82751f61 |
| checkpoint-4000/model-00002-of-00002.safetensors | Weights | 2.0 GB | becfa9a1b66e |
| checkpoint-4000/rng_state_0.pth | Weights | 15.4 KB | 9392d309ec79 |
| checkpoint-4000/rng_state_1.pth | Weights | 15.4 KB | 7dd56b7a2d69 |
| checkpoint-4000/rng_state_2.pth | Weights | 15.4 KB | d9d01f6f2b37 |
| checkpoint-4000/rng_state_3.pth | Weights | 15.4 KB | ab08833c85e3 |
| checkpoint-4000/scheduler.pt | Weights | 1.5 KB | ef93e83315ab |
| checkpoint-4000/training_args.bin | Weights | 8.0 KB | 05b269a25a90 |
| checkpoint-5000/model-00001-of-00002.safetensors | Weights | 5.0 GB | 9e578ac86782 |
| checkpoint-5000/model-00002-of-00002.safetensors | Weights | 2.0 GB | d6e84a0dfafe |
| checkpoint-5000/rng_state_0.pth | Weights | 15.4 KB | 38b5817e21a1 |
| checkpoint-5000/rng_state_1.pth | Weights | 15.4 KB | 53681794d300 |
| checkpoint-5000/rng_state_2.pth | Weights | 15.4 KB | de4377c87101 |
| checkpoint-5000/rng_state_3.pth | Weights | 15.4 KB | 497e39d3bf98 |
| checkpoint-5000/scheduler.pt | Weights | 1.5 KB | 7a16e6243ef7 |
| checkpoint-5000/training_args.bin | Weights | 8.0 KB | 05b269a25a90 |
| model-00001-of-00002.safetensors | Weights | 5.0 GB | 9e578ac86782 |
| model-00002-of-00002.safetensors | Weights | 2.0 GB | d6e84a0dfafe |
| training_args.bin | Weights | 8.0 KB | 05b269a25a90 |
| checkpoint-1000/config.json | Configuration | 3.2 KB | — |
| checkpoint-1000/embodiment_id.json | Configuration | 2.2 KB | — |
| checkpoint-1000/experiment_cfg/conf.yaml | Configuration | 6.8 KB | — |
| checkpoint-1000/experiment_cfg/config.yaml | Configuration | 6.8 KB | — |
| checkpoint-1000/experiment_cfg/dataset_statistics.json | Configuration | 5.3 KB | — |
| checkpoint-1000/experiment_cfg/final_model_config.json | Configuration | 2.5 KB | — |
| checkpoint-1000/experiment_cfg/final_processor_config.json | Configuration | 2.6 MB | — |
| checkpoint-1000/model.safetensors.index.json | Configuration | 192.8 KB | — |
| checkpoint-1000/processor_config.json | Configuration | 27.9 KB | — |
| checkpoint-1000/statistics.json | Configuration | 4.3 MB | — |
| checkpoint-1000/trainer_state.json | Configuration | 14.4 KB | — |
| checkpoint-1000/wandb_config.json | Configuration | 96 B | — |
| checkpoint-1000/zero_to_fp32.py | Configuration | 33.3 KB | — |
| checkpoint-2000/config.json | Configuration | 3.2 KB | — |
| checkpoint-2000/embodiment_id.json | Configuration | 2.2 KB | — |
| checkpoint-2000/experiment_cfg/conf.yaml | Configuration | 6.8 KB | — |
| checkpoint-2000/experiment_cfg/config.yaml | Configuration | 6.8 KB | — |
| checkpoint-2000/experiment_cfg/dataset_statistics.json | Configuration | 5.3 KB | — |
| checkpoint-2000/experiment_cfg/final_model_config.json | Configuration | 2.5 KB | — |
| checkpoint-2000/experiment_cfg/final_processor_config.json | Configuration | 2.6 MB | — |
| checkpoint-2000/model.safetensors.index.json | Configuration | 192.8 KB | — |
| checkpoint-2000/processor_config.json | Configuration | 27.9 KB | — |
| checkpoint-2000/statistics.json | Configuration | 4.3 MB | — |
| checkpoint-2000/trainer_state.json | Configuration | 28.3 KB | — |
| checkpoint-2000/wandb_config.json | Configuration | 96 B | — |
| checkpoint-2000/zero_to_fp32.py | Configuration | 33.3 KB | — |
| checkpoint-3000/config.json | Configuration | 3.2 KB | — |
| checkpoint-3000/embodiment_id.json | Configuration | 2.2 KB | — |
| checkpoint-3000/experiment_cfg/conf.yaml | Configuration | 6.8 KB | — |
| checkpoint-3000/experiment_cfg/config.yaml | Configuration | 6.8 KB | — |
| checkpoint-3000/experiment_cfg/dataset_statistics.json | Configuration | 5.3 KB | — |
| checkpoint-3000/experiment_cfg/final_model_config.json | Configuration | 2.5 KB | — |
| checkpoint-3000/experiment_cfg/final_processor_config.json | Configuration | 2.6 MB | — |
| checkpoint-3000/model.safetensors.index.json | Configuration | 192.8 KB | — |
| checkpoint-3000/processor_config.json | Configuration | 27.9 KB | — |
| checkpoint-3000/statistics.json | Configuration | 4.3 MB | — |
| checkpoint-3000/trainer_state.json | Configuration | 42.3 KB | — |
| checkpoint-3000/wandb_config.json | Configuration | 96 B | — |
| checkpoint-3000/zero_to_fp32.py | Configuration | 33.3 KB | — |
| checkpoint-4000/config.json | Configuration | 3.2 KB | — |
| checkpoint-4000/embodiment_id.json | Configuration | 2.2 KB | — |
| checkpoint-4000/experiment_cfg/conf.yaml | Configuration | 6.8 KB | — |
| checkpoint-4000/experiment_cfg/config.yaml | Configuration | 6.8 KB | — |
| checkpoint-4000/experiment_cfg/dataset_statistics.json | Configuration | 5.3 KB | — |
| checkpoint-4000/experiment_cfg/final_model_config.json | Configuration | 2.5 KB | — |
| checkpoint-4000/experiment_cfg/final_processor_config.json | Configuration | 2.6 MB | — |
| checkpoint-4000/model.safetensors.index.json | Configuration | 192.8 KB | — |
| checkpoint-4000/processor_config.json | Configuration | 27.9 KB | — |
| checkpoint-4000/statistics.json | Configuration | 4.3 MB | — |
| checkpoint-4000/trainer_state.json | Configuration | 56.4 KB | — |
| checkpoint-4000/wandb_config.json | Configuration | 96 B | — |
| checkpoint-4000/zero_to_fp32.py | Configuration | 33.3 KB | — |
| checkpoint-5000/config.json | Configuration | 3.2 KB | — |
| checkpoint-5000/embodiment_id.json | Configuration | 2.2 KB | — |
| checkpoint-5000/experiment_cfg/conf.yaml | Configuration | 6.8 KB | — |
| checkpoint-5000/experiment_cfg/config.yaml | Configuration | 6.8 KB | — |
| checkpoint-5000/experiment_cfg/dataset_statistics.json | Configuration | 5.3 KB | — |
| checkpoint-5000/experiment_cfg/final_model_config.json | Configuration | 2.5 KB | — |
| checkpoint-5000/experiment_cfg/final_processor_config.json | Configuration | 2.6 MB | — |
| checkpoint-5000/model.safetensors.index.json | Configuration | 192.8 KB | — |
| checkpoint-5000/processor_config.json | Configuration | 27.9 KB | — |
| checkpoint-5000/statistics.json | Configuration | 4.3 MB | — |
| checkpoint-5000/trainer_state.json | Configuration | 70.4 KB | — |
| checkpoint-5000/wandb_config.json | Configuration | 96 B | — |
| checkpoint-5000/zero_to_fp32.py | Configuration | 33.3 KB | — |
| config.json | Configuration | 3.2 KB | — |
| experiment_cfg/conf.yaml | Configuration | 6.8 KB | — |
| experiment_cfg/config.yaml | Configuration | 6.8 KB | — |
| experiment_cfg/dataset_statistics.json | Configuration | 5.3 KB | — |
| experiment_cfg/final_model_config.json | Configuration | 2.5 KB | — |
| experiment_cfg/final_processor_config.json | Configuration | 2.6 MB | — |
| model.safetensors.index.json | Configuration | 192.8 KB | — |
| processor/embodiment_id.json | Configuration | 2.2 KB | — |
| processor/processor_config.json | Configuration | 27.9 KB | — |
| processor/statistics.json | Configuration | 4.3 MB | — |
| wandb_config.json | Configuration | 96 B | — |
| checkpoint-1000/latest | Other | 15 B | — |
| checkpoint-2000/latest | Other | 15 B | — |
| checkpoint-3000/latest | Other | 15 B | — |
| checkpoint-4000/latest | Other | 15 B | — |
| checkpoint-5000/latest | Other | 15 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 41.8 GB
Download from Mango Cloud
Released by Mango Cloud through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 41.8 GB |
| 16-bit | 6.3 GB |
| 8-bit | 3.2 GB |
| 4-bit | 1.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About gr00t-n1.7-libero-90-k4-single-relation-causal-vlm-rank8
How much GPU memory does gr00t-n1.7-libero-90-k4-single-relation-causal-vlm-rank8 need?
About 7.6 GB at 16-bit and 1.9 GB at 4-bit: the weights (3.2B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run gr00t-n1.7-libero-90-k4-single-relation-causal-vlm-rank8 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.