← Sinan Lab › Models › Spirit v1.5
Spirit AI

Spirit v1.5

5.4B Commercial use OK 8/8 verified

Facts

Released
2026-01 1 Source
Parameters
5.4 B 1 Source
Architecture
VLM + action expert 0 Source
License
Code MIT (README); model card tagged apache-2.0 2 Source
Commercial
Commercial use OK 0 Source
Weights
huggingface.co ↗ 1 Source
Code
github.com ↗ 1 Source
Paper
spirit-ai.com ↗ 0 Source
Input modalities
rgb · language · state 0 Source
Action space
Action chunk output 0 Source
Cross-embodiment
Table30 benchmark tasks; README lists no embodiments or training hours 0 Source
Pretraining data (hours)
Unverified 0 Source
Target forms
Single arm · Dual arm 0 Source
Architecture · Qwen3-VL backbone + DiT action head + policy API; ranked first on the RoboChallenge Table2026 leaderboard since 01-11-30 (self-reported by the site)
Sources · 2 sources
release_date,license,arch_notes,code_url https://github.com/Spirit-AI-Team/spirit-v1.5 Official page · Fetched 2026-09-05 · No snapshot stored yet README: released 2026-01; MIT; Qwen3-VL backbone + DiT head; #1 on RoboChallenge Table30 as of Jan 11, 2026
params_b,weights_url,license https://huggingface.co/api/models/Spirit-AI-robotics/Spirit-v1.5 Model hub page · Fetched 2026-09-05 · No snapshot stored yet safetensors 5,400,901,236(F32);license: apache-2.0;createdAt 2026-01-11

Activity signals

Public counters fetched daily from GitHub, Hugging Face and ModelScope. Numbers only; no judgement. · fetched 2026-10-31

GitHub stars
670
+7 / 30 d
Commits · 90 d
0
last push 156 d ago
HF downloads · 30 d
178
all-time 817 · 32 likes
Weights last modified
2026-01-11
294 d ago
GitHubSpirit-AI-Team/spirit-v1.5 · 41 forks · 4 open issues · no GitHub release
ModelScopeSpirit-AI-robotics/Spirit-v1.5 · 165 downloads · updated 2026-01-12 · same org as Hugging Face
stars · last 30 d

Public benchmark scores

No public benchmark score recorded for this model yet (we only copy numbers printed in a paper, README or model card).

Deployment recipe

No recipe yet. We publish only steps that actually ran on a rented GPU with a measured latency; this model has not been through that yet.

Record history

2026-09-05
Sources fetched
release_date,license,arch_notes,code_url · params_b,weights_url,license

Latency & cost

cost = p50 ms ÷ 1000 × rental ÷ 3600 × 1000
Hardwarep50 msp95 msPeak VRAMCost per 1k inferences ¥samples
NVIDIA RTX 4090
¥1.68/h · GongJi Compute (2026)
— — — — no latency data No data
NVIDIA RTX 5090
¥2.4/h · Runyun 2.4 / GongJi 2.5 / Paratera Cloud 2.98 (2026)
— — — — no latency data No data
NVIDIA A100 80GB
no rental price
— — — — no latency data No data
NVIDIA Jetson AGX Thor
no rental price
— — — — no latency data No data
NVIDIA H100 80GB
no rental price
— — — — no latency data No data
NVIDIA A800 80GB
no rental price
— — — — no latency data No data
No latency measurements for this model yet · Data comes from literature, maintainer runs, or crowd CLI uploads. None exist so far.

Compatibility

Colored only where we hold evidence. An amber dot means the vendor declares this form as a target; that is a claim, not a verified compatibility.

Unitree G1Unitree H1AgiBot Genie G1AgileX Piper armSO-101Franka FR3 / PandaFourier GR-2WidowX 250 SGoogle Robot(Everyday Robots)ALOHA 2 / Cobot Magic (dual-arm)Galaxea R1 ProFranka Emika Panda
Spirit v1.5
Legend Officially supportedCommunity reproducedFine-tunable in theoryUnsupportedUnknown Vendor-declared target form 0 / 12 cells with a definite status

Reproduction records

Did this model run on your robot? Report it with a link (log, video or repo). Records are reviewed by the maintainers; a verified “works” or “works after fine-tuning” upgrades the matrix cell to “community verified” with your link as evidence. Anonymous is fine; nothing but the fields below is stored.

No verified record yet for this model.

SinanLab · Sinan LabClear direction, grounded judgement.