Llama-V-JEPA-LM-Qwen3-1.7B

Base language model: Qwen3-1.7B (Apache-2.0). The name begins with "Llama" because the training data include the FGQA split of PLM-Video-Human, an output of Lla

Base language model: Qwen3-1.7B (Apache-2.0). The name begins with "Llama" because the training data include the FGQA split of PLM-Video-Human, an output of Lla

Hugging Face Likes 7 · Hugging Face Trending Score 7 · Hugging Face Downloads 0

License: Commercial Use Allowed · ComfyUI: Not Available · VRAM: ≈5 GB (Estimated)

Reasons

  • Hugging Face world-model tag
  • Score 48 (freshness 15 / source 5 / heat 0 / ComfyUI 0 / VRAM 13 / demo 5 / license 10)

Usage

  • Estimate: 2.0B parameters, BF16 weights require approximately 4.1 GB, plus inference overhead of about 5 GB (excluding offloading).

Risks

  • VRAM estimates are based on parameter count; actual usage depends on resolution, duration, and offloading settings.
  • Figures stated in the model card or by the authors have not been independently verified.

Open

抱脸 world-model 标签

Explore the latest AI Radar updates