-
sahilchachra/Shieldstral-1.0-3B-MXFP4
Image-Text-to-Text • 1B • Updated • 32 -
sahilchachra/Shieldstral-1.0-3B-MXFP8
Image-Text-to-Text • 1B • Updated • 18 -
sahilchachra/Shieldstral-1.0-3B-INT8
Image-Text-to-Text • 1B • Updated • 35 -
sahilchachra/Shieldstral-1.0-3B-INT4
Image-Text-to-Text • 1.0B • Updated • 18
🤝 Open to Collab
Sahil Chachra
sahilchachra
AI & ML interests
Vision-Language Models (VLMs) for real-time video analytics, multi-camera inference pipelines, prompt engineering and frame-batching optimization for production deployment, edge/GPU
benchmarking (vLLM, Qwen-VL family), and applied computer vision for retail/QSR usecases.
Recent Activity
updated a collection 2 days ago
Shieldstral updated a collection 2 days ago
Shieldstral updated a collection 2 days ago
ShieldstralOrganizations
-
sahilchachra/Shieldstral-1.0-3B-MXFP4
Image-Text-to-Text • 1B • Updated • 32 -
sahilchachra/Shieldstral-1.0-3B-MXFP8
Image-Text-to-Text • 1B • Updated • 18 -
sahilchachra/Shieldstral-1.0-3B-INT8
Image-Text-to-Text • 1B • Updated • 35 -
sahilchachra/Shieldstral-1.0-3B-INT4
Image-Text-to-Text • 1.0B • Updated • 18
models 125
sahilchachra/Shieldstral-1.0-3B-MXFP4
Image-Text-to-Text • 1B • Updated • 32
sahilchachra/Shieldstral-1.0-3B-INT8
Image-Text-to-Text • 1B • Updated • 35
sahilchachra/Shieldstral-1.0-3B-INT4
Image-Text-to-Text • 1.0B • Updated • 18
sahilchachra/Shieldstral-1.0-3B-MXFP8
Image-Text-to-Text • 1B • Updated • 18
sahilchachra/ThinkingCap-Qwen3.6-27B-AWQ
Image-Text-to-Text • 27B • Updated • 1.19k • 3
sahilchachra/ThinkingCap-Qwen3.6-27B-NVFP4A16
Image-Text-to-Text • 28B • Updated • 474 • 2
sahilchachra/Agents-A1-W4A16
Image-Text-to-Text • 35B • Updated • 1.91k
sahilchachra/Agents-A1-NVFP4A16
Image-Text-to-Text • 35B • Updated • 189
sahilchachra/Mage-VL-AWQ
Image-Text-to-Text • 5B • Updated • 587
sahilchachra/Mage-VL-NVFP4A16
Image-Text-to-Text • 5B • Updated • 111
datasets 0
None public yet