Open-weight model
pi05_insert_gear_in_gripper_expert_only_step4000
by Fanqi Robo fanqi-robo/pi05_insert_gear_in_gripper_expert_only_step4000
pi05_insert_gear_in_gripper_expert_only_step4000 is an open-weight model from Fanqi Robo. It has 4.1B parameters. At 16-bit it needs about 9.9 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 pi05_insert_gear_in_gripper_expert_only_step4000 (4.1B 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 | 8.3 GB | 9.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 4.1 GB | 5.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.1 GB | 2.5 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.
Identity and Version
- Repository
- fanqi-robo/pi05_insert_gear_in_gripper_expert_only_step4000
- Publisher
- Fanqi Robo
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 4.1B parameters
- Languages
- Not stated by the source
- Revision
- a6ee8f973ab502c46b1286790956d6a259cad678
- First published
- 2026-10-01
- Last updated
- 2026-10-01
Files and Weights
8 files, 9.4 GB in total. The weights are 3 files totalling 9.4 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 9.4 GB | e984579e46d4 |
| policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 9.3 KB | 0a1c68578d73 |
| policy_preprocessor_step_2_normalizer_processor.safetensors | Weights | 9.3 KB | 0a1c68578d73 |
| config.json | Configuration | 2.9 KB | — |
| policy_postprocessor.json | Configuration | 663 B | — |
| policy_preprocessor.json | Configuration | 1.9 KB | — |
| train_config.json | Configuration | 8.0 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 9.4 GB
Released by Fanqi Robo through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 9.4 GB |
| 16-bit | 8.3 GB |
| 8-bit | 4.1 GB |
| 4-bit | 2.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About pi05_insert_gear_in_gripper_expert_only_step4000
How much GPU memory does pi05_insert_gear_in_gripper_expert_only_step4000 need?
About 9.9 GB at 16-bit and 2.5 GB at 4-bit: the weights (4.1B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run pi05_insert_gear_in_gripper_expert_only_step4000 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.