# GigaBrain-0.7-3.5B-Base by GigaAI: Open-Weight Model Source: https://savrn.com/models/gigabrain-0-7-3-5b-base Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve GigaBrain-0.7-3.5B-Base (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 | 8.2 GB | 9.9 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 4.1 GB | 4.9 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 2.1 GB | 2.5 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 24, 2026. [GigaBrain-0.7-3.5B-Base on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/gigabrain-0-7-3-5b-base/gpus) ## Model Card By GigaAI, published under apache-2.0, revision 2936d6f26327. ### GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0) [![Project](https://img.shields.io/badge/Project-Page-99cc2)](https://gigaai.cc/blog/gigabrain07) [![arXiv](https://img.shields.io/badge/arXiv-2608.15875-b31b1b.svg)](https://arxiv.org/abs/2608.15875) [![Paper](https://img.shields.io/badge/Paper-Technical_Report-99cc2)](https://github.com/open-gigaai/giga-brain-0/blob/main/tech_report/GigaBrain-0.7.pdf) [![Models](https://img.shields.io/badge/HuggingFace-Models-yellow?logo=huggingface)](https://huggingface.co/open-gigaai/GigaBrain-0.7-3.5B-Base) [![DataSets](https://img.shields.io/badge/HuggingFace-Data-yellow?logo=huggingface)](https://huggingface.co/datasets/open-gigaai/GigaBrain-0.7-SampleData) ### Introduction [Read the full model card (211 words)](https://savrn.com/models/gigabrain-0-7-3-5b-base/card) ## Identity and Version Repository open-gigaai/GigaBrain-0.7-3.5B-Base Publisher GigaAI Task Robotics Modality Control Library diffusers Parameters 4.1B parameters Languages en Revision 2936d6f263279a58d4f9153b2efa597812c194cb First published 2026-08-24 Last updated 2026-08-25 ## Files and Weights 10 files, 33.0 GB in total. The weights are 5 files totalling 33.0 GB in bin, safetensors. Weights5 files · 33.0 GB Configuration2 files · 137.6 KB Documentation1 file · 3.0 KB Other1 file · 2.3 MB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | diffusion_pytorch_model-00001-of-00004.safetensors | Weights | 5.0 GB | 223bda49a0a0 | | diffusion_pytorch_model-00002-of-00004.safetensors | Weights | 4.9 GB | 9fb0122adfd0 | | diffusion_pytorch_model-00003-of-00004.safetensors | Weights | 4.2 GB | 7db9419afed9 | | diffusion_pytorch_model-00004-of-00004.safetensors | Weights | 2.4 GB | 02506a600cbf | | diffusion_pytorch_model.bin | Weights | 16.5 GB | d8270bd58cf1 | | config.json | Configuration | 1.9 KB | — | | diffusion_pytorch_model.safetensors.index.json | Configuration | 135.7 KB | — | | README.md | Documentation | 3.0 KB | — | | gigabrain07_arch.png | Other | 2.3 MB | 39da63661083 | | .gitattributes | Repository | 1.6 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 33.0 GB [Download from GigaAI](https://huggingface.co/open-gigaai/GigaBrain-0.7-3.5B-Base) Released by GigaAI through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by arXiv:2608.15875 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 33.0 GB | | 16-bit | 8.2 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 GigaBrain-0.7-3.5B-Base ### How much GPU memory does GigaBrain-0.7-3.5B-Base 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 GigaBrain-0.7-3.5B-Base 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. ### Can I use GigaBrain-0.7-3.5B-Base commercially? Yes. GigaBrain-0.7-3.5B-Base is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ## Similar Models Model · Robotics ### [unlv_vla_policy](https://savrn.com/models/unlv-vla-policy) [Jinseok Kim](https://savrn.com/model-publishers/kemjensak) π₀.₅ (Pi05) is a Vision-Language-Action model from Physical Intelligence designed for open-world generalization: it evolves π₀ to generalize to entirely new environments and situations that were never seen during training. The LeRobot implementation is adapted from their open-source OpenPI repository. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot pi05 guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and… Open weights apache-2.0 4.1B parameters lerobot [View model](https://savrn.com/models/unlv-vla-policy) Model · Robotics ### [pi05_telearms_v4_fullft_lr7.07e-5](https://savrn.com/models/pi05-telearms-v4-fullft-lr7-07e-5) [Helen Wang](https://savrn.com/model-publishers/helen9975) π₀.₅ (lerobot/pi05base) full fine-tune on mliu48/telearms-yam-cube-v4 (53,832 bimanual YAM demonstrations, 48 tasks, 30 Hz, 3 × 224×224 cameras). LeRobot 0.6.1 @ e40b58a8 with the repo's patch (tools/installlerobotpatch.py). - Full fine-tune (LLM + vision + action expert), bf16, gradient checkpointing. - 16 × H100 (2 nodes × 8), batch 16/GPU (global 256), 99,486 steps (one selected-data epoch). - Peak LR 7.07e-5, cosine decay to 7.07e-06, 1,000 warmup steps; relative actions (absolute grippers). Final checkpoint (step 99,486), training/evaluatepi.py suite settings in the RoboEval YAM simulator: 10 episodes per task, seeds 900000001–900000010, 1,800-step limit, 25-step action chunks, success… Open weights 4.1B parameters lerobot [View model](https://savrn.com/models/pi05-telearms-v4-fullft-lr7-07e-5) Model · Robotics ### [pi05-real-workbench-preset-3view-layout-reconstruction-60k](https://savrn.com/models/pi05-real-workbench-preset-3view-layout-reconstruction-60k) [Jaehyun Kang](https://savrn.com/model-publishers/jaehyunkang) Final checkpoint after 60,000 optimization steps. This is a trained policy, not an evaluation result. Policy weights, policy configuration, preprocessing/postprocessing and normalization states are at the repository root. Training resume files are in trainingstate/. Host-specific paths were removed from JSON metadata; supply local dataset/output paths when resuming. The tokenizer reference points to google/paligemma-3b-pt-224 (training revision 35e4f46485b4d07967e7e9935bc3786aad50687c). For subtask models, supply the corresponding per-frame subtask as the policy task text. For 3-view models also supply the dataset-defined keyframe image. No real-robot evaluation metrics are claimed here.… Open weights 4.1B parameters lerobot [View model](https://savrn.com/models/pi05-real-workbench-preset-3view-layout-reconstruction-60k) Model · Robotics ### [pi05-real-workbench-preset-3view-object-identification-60k](https://savrn.com/models/pi05-real-workbench-preset-3view-object-identification-60k) [Jaehyun Kang](https://savrn.com/model-publishers/jaehyunkang) Final checkpoint after 60,000 optimization steps. This is a trained policy, not an evaluation result. Policy weights, policy configuration, preprocessing/postprocessing and normalization states are at the repository root. Training resume files are in trainingstate/. Host-specific paths were removed from JSON metadata; supply local dataset/output paths when resuming. The tokenizer reference points to google/paligemma-3b-pt-224 (training revision 35e4f46485b4d07967e7e9935bc3786aad50687c). For subtask models, supply the corresponding per-frame subtask as the policy task text. For 3-view models also supply the dataset-defined keyframe image. No real-robot evaluation metrics are claimed here.… Open weights 4.1B parameters lerobot [View model](https://savrn.com/models/pi05-real-workbench-preset-3view-object-identification-60k) Model · Robotics ### [train_800_dense__bbox__blackout__sim__all_cameras__live__pi05__seed_0](https://savrn.com/models/train-800-dense-bbox-blackout-sim-all-cameras-live-pi05-seed-0) [Mim Chess Vlas](https://savrn.com/model-publishers/mim-chess-vlas) π₀.₅ (Pi05) is a Vision-Language-Action model from Physical Intelligence designed for open-world generalization: it evolves π₀ to generalize to entirely new environments and situations that were never seen during training. The LeRobot implementation is adapted from their open-source OpenPI repository. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot pi05 guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and… Open weights apache-2.0 4.1B parameters lerobot [View model](https://savrn.com/models/train-800-dense-bbox-blackout-sim-all-cameras-live-pi05-seed-0) Model · Robotics ### [train_800_sparse__no_mask__ur5e__pi05__seed_0__b_b30](https://savrn.com/models/train-800-sparse-no-mask-ur5e-pi05-seed-0-b-b30) [Mim Chess Vlas](https://savrn.com/model-publishers/mim-chess-vlas) π₀.₅ (Pi05) is a Vision-Language-Action model from Physical Intelligence designed for open-world generalization: it evolves π₀ to generalize to entirely new environments and situations that were never seen during training. The LeRobot implementation is adapted from their open-source OpenPI repository. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot pi05 guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and… Open weights apache-2.0 4.1B parameters lerobot [View model](https://savrn.com/models/train-800-sparse-no-mask-ur5e-pi05-seed-0-b-b30) ## GigaAI [All models and datasets](https://savrn.com/model-publishers/open-gigaai) ## Versions - [2936d6f26327](https://savrn.com/models/gigabrain-0-7-3-5b-base/versions/2936d6f26327) · current 2026-09-18 ## Explore More - [All robotics models](https://savrn.com/models/tasks/robotics) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-21. - [Hugging Face record](https://huggingface.co/open-gigaai/GigaBrain-0.7-3.5B-Base) - [How the hub is built](https://savrn.com/model-hub/methodology)