Hy-Embodied-VLM-1.0
Model overview
Hy-Embodied-VLM-1.0
Tencent's open-weight Hy-Embodied vision-language model for embodied visual understanding and spatial and physical reasoning.
multimodalvision-languagereasoningagentworld modelrobotics / embodied AIevaluationrobotics / embodied AIlocal inference
Representative version
Hy-Embodied-VLM-1.0
| Company | Tencent / Hunyuan |
|---|---|
| Release | 2026-07-15 |
| Release type | Model checkpoint release |
| Parameters | 30B / 3B active |
| Architecture | HYV3VLForConditionalGeneration (HYV3ForCausalLM MoE + Hy-ViT2 vision encoder) |
| Context | 32,768 |
| Input modalities | text / image / video |
| Output modalities | text |
| Tool use / function calling | Tool use: Not disclosed; Function calling: Not disclosed |
| Structured output / reasoning | Confirmed: Reasoning |
| Vision / audio / video | Confirmed: Vision, Video; Not shown: Audio |
| Open weights / License | Weights available / Apache-2.0 License sourcetencent-hy-embodied-vlm-1-0-current · 2026-08-04 |
| Vendor API | Not disclosed API source pending verification |
| OpenRouter | Not separately listed on OpenRouter |
| Pricing | No reliable public source |
| Benchmark | No reliable public source |
| Public signals | 1 activity snapshot |
| Use cases | Embodied visual understanding / Spatial reasoning / Physical reasoning / Local research inference |
| Claim evidence | Release event / Model specifications / Weight checkpointtencent/Hy-Embodied-VLM-1.0Hy-Embodied-VLM-1.0 · 2026-07-15 · Hy-Embodied-VLM-1.0 · Hy-Embodied-VLM-1.0 · Hy-Embodied-VLM-1.0 |
OpenRouter
Pricing / context / availability
| OpenRouter | Not separately listed on OpenRouter |
|---|---|
| OpenRouter listing | Not separately listed in the current OpenRouter public list |
| Mapped version | Hy-Embodied-VLM-1.0 tencent-hy-embodied-vlm-1-0-current |
| Pricing | No reliable public source |
| Context | 32768 |
| Speed/Latency | No reliable public source |
| Snapshot time | 2026-08-11T06:28:09.895Z |
| Source | View source |
Verified limitations
Usage boundaries
- The official model card does not establish a commercial API, OpenRouter availability, independent rankings, or production reliability.
Public activity counters
Hugging Face model-card activity snapshot
| Platform | Entry | Last-month downloads | Current likes | Current Spaces | Time | Source |
|---|---|---|---|---|---|---|
| huggingface Current HF activity snapshot | tencent/Hy-Embodied-VLM-1.0 | 1,117 | 23 | 0 | View source |
Downloads are Hugging Face's trailing-month counter; likes and Spaces are snapshots at collection time.
Missing public information
Public information not yet available
Not listed on OpenRouterNo reliable benchmark sourceNo linkable model-specific reviewSpeed/latency not disclosed