Open-weight model
gr00t-n1.6-pick-apple-left-locomanip-more-h50
by Byeonghwi Kim byeonghwikim/gr00t-n1.6-pick-apple-left-locomanip-more-h50
gr00t-n1.6-pick-apple-left-locomanip-more-h50 is an open-weight model from Byeonghwi Kim. It has 3.3B parameters. At 16-bit it needs about 7.9 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Parameters3.3B
Context—
Weights179.6 GB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve gr00t-n1.6-pick-apple-left-locomanip-more-h50 (3.3B 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 | 6.6 GB | 7.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 3.3 GB | 3.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 1.6 GB | 2.0 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 18, 2026.
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Gr00tN1d6
- Hidden size
- 1,024
- Stored precision
- bfloat16
- Model type
- Gr00tN1d6
Identity and Version
- Repository
- byeonghwikim/gr00t-n1.6-pick-apple-left-locomanip-more-h50
- Publisher
- Byeonghwi Kim
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 3.3B parameters
- Languages
- Not stated by the source
- Revision
- 446d5cf28ca38f5c01f7875875b8ac39312c2b27
- First published
- 2026-10-11
- Last updated
- 2026-10-12
Files and Weights
139 files, 179.6 GB in total. The weights are 65 files totalling 179.6 GB in bin, pt, pth, safetensors.
Weights65 files · 179.6 GB
Configuration68 files · 5.7 MB
Other5 files · 80 B
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoint-10000/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 04ad3236d435 |
| checkpoint-10000/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 4d9598157ae1 |
| checkpoint-10000/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 8f6ab1454ff2 |
| checkpoint-10000/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 7d862c744bf9 |
| checkpoint-10000/global_step10000/mp_rank_00_model_states.pt | Weights | 9.9 GB | 72475060ca1f |
| checkpoint-10000/model-00001-of-00002.safetensors | Weights | 5.0 GB | a801cdc0c9ca |
| checkpoint-10000/model-00002-of-00002.safetensors | Weights | 1.6 GB | 553b65ce510f |
| checkpoint-10000/rng_state_0.pth | Weights | 15.4 KB | 2c362b444345 |
| checkpoint-10000/rng_state_1.pth | Weights | 15.4 KB | a255c2d7ed0c |
| checkpoint-10000/rng_state_2.pth | Weights | 15.4 KB | 2bb969327386 |
| checkpoint-10000/rng_state_3.pth | Weights | 15.4 KB | b0c090db1ace |
| checkpoint-10000/scheduler.pt | Weights | 1.5 KB | e0d349884154 |
| checkpoint-10000/training_args.bin | Weights | 7.7 KB | 70204cf000b2 |
| checkpoint-20000/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 43db52006ddf |
| checkpoint-20000/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt | Weights | 4.9 GB | c0f6b5793ca4 |
| checkpoint-20000/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 7179c2f6c201 |
| checkpoint-20000/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt | Weights | 4.9 GB | c913fdb32582 |
| checkpoint-20000/global_step20000/mp_rank_00_model_states.pt | Weights | 9.9 GB | e895714c79bc |
| checkpoint-20000/model-00001-of-00002.safetensors | Weights | 5.0 GB | 80cf66d59984 |
| checkpoint-20000/model-00002-of-00002.safetensors | Weights | 1.6 GB | fb60633c6045 |
| checkpoint-20000/rng_state_0.pth | Weights | 15.4 KB | 2ebb7cae538f |
| checkpoint-20000/rng_state_1.pth | Weights | 15.4 KB | 7eed01900367 |
| checkpoint-20000/rng_state_2.pth | Weights | 15.4 KB | ed121133911d |
| checkpoint-20000/rng_state_3.pth | Weights | 15.4 KB | aedb6355e9a3 |
| checkpoint-20000/scheduler.pt | Weights | 1.5 KB | 68a951da1c96 |
| checkpoint-20000/training_args.bin | Weights | 7.7 KB | 70204cf000b2 |
| checkpoint-30000/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 174f4a0d8af3 |
| checkpoint-30000/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 1d646e9e95e7 |
| checkpoint-30000/global_step30000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 2da12e2a6d06 |
| checkpoint-30000/global_step30000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt | Weights | 4.9 GB | c94d27276445 |
| checkpoint-30000/global_step30000/mp_rank_00_model_states.pt | Weights | 9.9 GB | 79e74aa0f23d |
| checkpoint-30000/model-00001-of-00002.safetensors | Weights | 5.0 GB | 836d527a5662 |
| checkpoint-30000/model-00002-of-00002.safetensors | Weights | 1.6 GB | 694260ace231 |
| checkpoint-30000/rng_state_0.pth | Weights | 15.4 KB | 2e92decde0a2 |
| checkpoint-30000/rng_state_1.pth | Weights | 15.4 KB | c6b408e10ced |
| checkpoint-30000/rng_state_2.pth | Weights | 15.4 KB | f17efe6ad4d2 |
| checkpoint-30000/rng_state_3.pth | Weights | 15.4 KB | a566fca7d8b1 |
| checkpoint-30000/scheduler.pt | Weights | 1.5 KB | a475d3639528 |
| checkpoint-30000/training_args.bin | Weights | 7.7 KB | 70204cf000b2 |
| checkpoint-40000/global_step40000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 6eac2785a0f2 |
| checkpoint-40000/global_step40000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 53910436cf96 |
| checkpoint-40000/global_step40000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 96481ceb3a9f |
| checkpoint-40000/global_step40000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt | Weights | 4.9 GB | a87a0ec77228 |
| checkpoint-40000/global_step40000/mp_rank_00_model_states.pt | Weights | 9.9 GB | 02b0c78b12b4 |
| checkpoint-40000/model-00001-of-00002.safetensors | Weights | 5.0 GB | 20a94e6856c3 |
| checkpoint-40000/model-00002-of-00002.safetensors | Weights | 1.6 GB | b40aa773ad96 |
| checkpoint-40000/rng_state_0.pth | Weights | 15.4 KB | da13cb86356d |
| checkpoint-40000/rng_state_1.pth | Weights | 15.4 KB | 58fd9d9c347f |
| checkpoint-40000/rng_state_2.pth | Weights | 15.4 KB | d31fffd8773b |
| checkpoint-40000/rng_state_3.pth | Weights | 15.4 KB | da99d492f9af |
| checkpoint-40000/scheduler.pt | Weights | 1.5 KB | 67a4795ac838 |
| checkpoint-40000/training_args.bin | Weights | 7.7 KB | 70204cf000b2 |
| global_step50000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 443a68a94f88 |
| global_step50000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 6c9b6461f3e4 |
| global_step50000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt | Weights | 4.9 GB | f070362f9b4e |
| global_step50000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt | Weights | 4.9 GB | 5b145501608b |
| global_step50000/mp_rank_00_model_states.pt | Weights | 9.9 GB | ff9a83591c67 |
| model-00001-of-00002.safetensors | Weights | 5.0 GB | 94ea2f7597df |
| model-00002-of-00002.safetensors | Weights | 1.6 GB | 28187f841b2e |
| rng_state_0.pth | Weights | 15.4 KB | d23c536aa9c9 |
| rng_state_1.pth | Weights | 15.4 KB | bd8e2b7d2912 |
| rng_state_2.pth | Weights | 15.4 KB | 41ad25787a37 |
| rng_state_3.pth | Weights | 15.4 KB | b127f7e91258 |
| scheduler.pt | Weights | 1.5 KB | 449f1d48ece5 |
| training_args.bin | Weights | 7.7 KB | 70204cf000b2 |
| checkpoint-10000/config.json | Configuration | 1.8 KB | — |
| checkpoint-10000/embodiment_id.json | Configuration | 260 B | — |
| checkpoint-10000/experiment_cfg/conf.yaml | Configuration | 6.5 KB | — |
| checkpoint-10000/experiment_cfg/config.yaml | Configuration | 9.2 KB | — |
| checkpoint-10000/experiment_cfg/dataset_statistics.json | Configuration | 13.9 KB | — |
| checkpoint-10000/experiment_cfg/final_model_config.json | Configuration | 1.4 KB | — |
| checkpoint-10000/experiment_cfg/final_processor_config.json | Configuration | 177.3 KB | — |
| checkpoint-10000/model.safetensors.index.json | Configuration | 121.8 KB | — |
| checkpoint-10000/processor_config.json | Configuration | 13.2 KB | — |
| checkpoint-10000/statistics.json | Configuration | 276.8 KB | — |
| checkpoint-10000/trainer_state.json | Configuration | 137.7 KB | — |
| checkpoint-10000/wandb_config.json | Configuration | 93 B | — |
| checkpoint-10000/zero_to_fp32.py | Configuration | 33.3 KB | — |
| checkpoint-20000/config.json | Configuration | 1.8 KB | — |
| checkpoint-20000/embodiment_id.json | Configuration | 260 B | — |
| checkpoint-20000/experiment_cfg/conf.yaml | Configuration | 6.5 KB | — |
| checkpoint-20000/experiment_cfg/config.yaml | Configuration | 9.2 KB | — |
| checkpoint-20000/experiment_cfg/dataset_statistics.json | Configuration | 13.9 KB | — |
| checkpoint-20000/experiment_cfg/final_model_config.json | Configuration | 1.4 KB | — |
| checkpoint-20000/experiment_cfg/final_processor_config.json | Configuration | 177.3 KB | — |
| checkpoint-20000/model.safetensors.index.json | Configuration | 121.8 KB | — |
| checkpoint-20000/processor_config.json | Configuration | 13.2 KB | — |
| checkpoint-20000/statistics.json | Configuration | 276.8 KB | — |
| checkpoint-20000/trainer_state.json | Configuration | 278.1 KB | — |
| checkpoint-20000/wandb_config.json | Configuration | 93 B | — |
| checkpoint-20000/zero_to_fp32.py | Configuration | 33.3 KB | — |
| checkpoint-30000/config.json | Configuration | 1.8 KB | — |
| checkpoint-30000/embodiment_id.json | Configuration | 260 B | — |
| checkpoint-30000/experiment_cfg/conf.yaml | Configuration | 6.5 KB | — |
| checkpoint-30000/experiment_cfg/config.yaml | Configuration | 9.2 KB | — |
| checkpoint-30000/experiment_cfg/dataset_statistics.json | Configuration | 13.9 KB | — |
| checkpoint-30000/experiment_cfg/final_model_config.json | Configuration | 1.4 KB | — |
| checkpoint-30000/experiment_cfg/final_processor_config.json | Configuration | 177.3 KB | — |
| checkpoint-30000/model.safetensors.index.json | Configuration | 121.8 KB | — |
| checkpoint-30000/processor_config.json | Configuration | 13.2 KB | — |
| checkpoint-30000/statistics.json | Configuration | 276.8 KB | — |
| checkpoint-30000/trainer_state.json | Configuration | 418.9 KB | — |
| checkpoint-30000/wandb_config.json | Configuration | 93 B | — |
| checkpoint-30000/zero_to_fp32.py | Configuration | 33.3 KB | — |
| checkpoint-40000/config.json | Configuration | 1.8 KB | — |
| checkpoint-40000/embodiment_id.json | Configuration | 260 B | — |
| checkpoint-40000/experiment_cfg/conf.yaml | Configuration | 6.5 KB | — |
| checkpoint-40000/experiment_cfg/config.yaml | Configuration | 9.2 KB | — |
| checkpoint-40000/experiment_cfg/dataset_statistics.json | Configuration | 13.9 KB | — |
| checkpoint-40000/experiment_cfg/final_model_config.json | Configuration | 1.4 KB | — |
| checkpoint-40000/experiment_cfg/final_processor_config.json | Configuration | 177.3 KB | — |
| checkpoint-40000/model.safetensors.index.json | Configuration | 121.8 KB | — |
| checkpoint-40000/processor_config.json | Configuration | 13.2 KB | — |
| checkpoint-40000/statistics.json | Configuration | 276.8 KB | — |
| checkpoint-40000/trainer_state.json | Configuration | 560.3 KB | — |
| checkpoint-40000/wandb_config.json | Configuration | 93 B | — |
| checkpoint-40000/zero_to_fp32.py | Configuration | 33.3 KB | — |
| config.json | Configuration | 1.8 KB | — |
| embodiment_id.json | Configuration | 260 B | — |
| experiment_cfg/conf.yaml | Configuration | 6.5 KB | — |
| experiment_cfg/config.yaml | Configuration | 9.2 KB | — |
| experiment_cfg/dataset_statistics.json | Configuration | 13.9 KB | — |
| experiment_cfg/final_model_config.json | Configuration | 1.4 KB | — |
| experiment_cfg/final_processor_config.json | Configuration | 177.3 KB | — |
| model.safetensors.index.json | Configuration | 121.8 KB | — |
| processor/embodiment_id.json | Configuration | 260 B | — |
| processor/processor_config.json | Configuration | 13.2 KB | — |
| processor/statistics.json | Configuration | 276.8 KB | — |
| processor_config.json | Configuration | 13.2 KB | — |
| statistics.json | Configuration | 276.8 KB | — |
| trainer_state.json | Configuration | 701.7 KB | — |
| wandb_config.json | Configuration | 93 B | — |
| zero_to_fp32.py | Configuration | 33.3 KB | — |
| checkpoint-10000/latest | Other | 16 B | — |
| checkpoint-20000/latest | Other | 16 B | — |
| checkpoint-30000/latest | Other | 16 B | — |
| checkpoint-40000/latest | Other | 16 B | — |
| latest | Other | 16 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 179.6 GB
Download from Byeonghwi Kim
Released by Byeonghwi Kim through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 179.6 GB |
| 16-bit | 6.6 GB |
| 8-bit | 3.3 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-n1.6-pick-apple-left-locomanip-more-h50
How much GPU memory does gr00t-n1.6-pick-apple-left-locomanip-more-h50 need?
About 7.9 GB at 16-bit and 2 GB at 4-bit: the weights (3.3B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run gr00t-n1.6-pick-apple-left-locomanip-more-h50 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.