🤝 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 about 5 hours ago
sahilchachra/Leanstral-1.5-119B-A6B-NVFP4 published a model about 5 hours ago
sahilchachra/Leanstral-1.5-119B-A6B-NVFP4 updated a model about 6 hours ago
sahilchachra/Leanstral-1.5-119B-A6B-BF16Organizations
-
sahilchachra/Qwythos-9B-Claude-Mythos-5-1M-AWQ
Text Generation • 9B • Updated • 3.45k • 2 -
sahilchachra/Qwythos-9B-Claude-Mythos-5-1M-NVFP4
Text Generation • 7B • Updated • 2.6k • 3 -
sahilchachra/Qwythos-9B-Claude-Mythos-5-1M-mxfp4-mlx
2B • Updated • 6.99k • 5 -
sahilchachra/Qwythos-9B-Claude-Mythos-5-1M-mxfp8-mlx
9B • Updated • 3.9k • 1
-
sahilchachra/LFM2.5-ColBERT-350M-fp16
Feature Extraction • 0.4B • Updated • 43 -
sahilchachra/LFM2.5-ColBERT-350M-mxfp4
Feature Extraction • 55.4M • Updated • 34 -
sahilchachra/LFM2.5-ColBERT-350M-mxfp8
Feature Extraction • 99.6M • Updated • 33 -
sahilchachra/LFM2.5-ColBERT-350M-int8
Feature Extraction • 99.6M • Updated • 74
-
sahilchachra/Unlimited-OCR-NVFP4
Image-Text-to-Text • 2B • Updated • 1.31k • 1 -
sahilchachra/Unlimited-OCR-GGUF
Image-Text-to-Text • 3B • Updated • 51.3k • 72 -
sahilchachra/unlimited-ocr-8bit-mlx
Image-Text-to-Text • 1B • Updated • 547 • 2 -
sahilchachra/unlimited-ocr-4bit-mlx
Image-Text-to-Text • 0.9B • Updated • 428 • 1
-
sahilchachra/LFM2.5-Embedding-350M-fp16
Sentence Similarity • 0.4B • Updated • 68 -
sahilchachra/LFM2.5-Embedding-350M-mxfp8
Sentence Similarity • 99.7M • Updated • 59 -
sahilchachra/LFM2.5-Embedding-350M-mxfp4
Sentence Similarity • 55.4M • Updated • 91 -
sahilchachra/LFM2.5-Embedding-350M-int8
Sentence Similarity • 99.7M • Updated • 133
-
sahilchachra/Unlimited-OCR-NVFP4
Image-Text-to-Text • 2B • Updated • 1.31k • 1 -
sahilchachra/Unlimited-OCR-GGUF
Image-Text-to-Text • 3B • Updated • 51.3k • 72 -
sahilchachra/unlimited-ocr-8bit-mlx
Image-Text-to-Text • 1B • Updated • 547 • 2 -
sahilchachra/unlimited-ocr-4bit-mlx
Image-Text-to-Text • 0.9B • Updated • 428 • 1
-
sahilchachra/Qwythos-9B-Claude-Mythos-5-1M-AWQ
Text Generation • 9B • Updated • 3.45k • 2 -
sahilchachra/Qwythos-9B-Claude-Mythos-5-1M-NVFP4
Text Generation • 7B • Updated • 2.6k • 3 -
sahilchachra/Qwythos-9B-Claude-Mythos-5-1M-mxfp4-mlx
2B • Updated • 6.99k • 5 -
sahilchachra/Qwythos-9B-Claude-Mythos-5-1M-mxfp8-mlx
9B • Updated • 3.9k • 1
-
sahilchachra/LFM2.5-Embedding-350M-fp16
Sentence Similarity • 0.4B • Updated • 68 -
sahilchachra/LFM2.5-Embedding-350M-mxfp8
Sentence Similarity • 99.7M • Updated • 59 -
sahilchachra/LFM2.5-Embedding-350M-mxfp4
Sentence Similarity • 55.4M • Updated • 91 -
sahilchachra/LFM2.5-Embedding-350M-int8
Sentence Similarity • 99.7M • Updated • 133
-
sahilchachra/LFM2.5-ColBERT-350M-fp16
Feature Extraction • 0.4B • Updated • 43 -
sahilchachra/LFM2.5-ColBERT-350M-mxfp4
Feature Extraction • 55.4M • Updated • 34 -
sahilchachra/LFM2.5-ColBERT-350M-mxfp8
Feature Extraction • 99.6M • Updated • 33 -
sahilchachra/LFM2.5-ColBERT-350M-int8
Feature Extraction • 99.6M • Updated • 74