🤝 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 model 2 days ago
sahilchachra/KAT-Coder-V2.5-Dev-W4A16 published a model 2 days ago
sahilchachra/KAT-Coder-V2.5-Dev-W4A16 updated a model 2 days ago
sahilchachra/KAT-Coder-V2.5-Dev-NVFP4A16Organizations
models 117
sahilchachra/KAT-Coder-V2.5-Dev-W4A16
Text Generation • 35B • Updated • 210 • 1
sahilchachra/KAT-Coder-V2.5-Dev-NVFP4A16
Text Generation • 20B • Updated • 289 • 2
sahilchachra/nanbeige4.2-3b-int8-mlx
Text Generation • 1B • Updated • 68
sahilchachra/nanbeige4.2-3b-int4-mlx
Text Generation • 0.7B • Updated • 74
sahilchachra/nanbeige4.2-3b-mxfp8-mlx
Text Generation • 1B • Updated • 129
sahilchachra/nanbeige4.2-3b-mxfp4-mlx
Text Generation • 0.8B • Updated • 141
sahilchachra/Qwen3.5-9B-English-trimmed
Text Generation • 8B • Updated • 19
sahilchachra/Qwen3.5-0.8B-English-trimmed
Text Generation • 0.5B • Updated • 44
sahilchachra/Qwythos-9B-v2-AWQ
Text Generation • 9B • Updated • 272 • 1
sahilchachra/ovisocr2-int4-mlx
Image-Text-to-Text • 0.2B • Updated • 107 • 1
datasets 0
None public yet