Llama-V-JEPA-LM-Llama3.2-1B is built on Meta's Llama-3.2-1B-Instruct. Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, I
Hugging Face Likes 7 · Hugging Face Trending Score 7 · Hugging Face Downloads 0
License: Commercial Use with Conditions · ComfyUI: Not Available · VRAM: ≈4 GB (Estimated)
Reasons
- Hugging Face world-model tag
- Score 45 (freshness 15 / source 5 / heat 0 / comfy 0 / vram 13 / demo 5 / license 7)
Usage
- Estimate: 1.5B parameters, BF16 weights require approximately 3.1 GB, plus inference overhead of about 4 GB (excluding offloading).
Risks
- VRAM usage is estimated based on parameter count; actual requirements depend on resolution, duration, and offloading settings.
- Figures stated in the model card or by the author have not been independently verified.