AI & ML interests
None defined yet.
Recent Activity
Organization Card
VinRobotics - Edge AI & Model Optimization
We optimize and deploy LLMs, ASR, VLM and VLA (Vision-Language-Action) models on real-world systems.
What we do
- Optimization: quantization (INT8/INT4/FP8/NVFP4), pruning, distillation, ...
- Deployment: VLLM, TensorRT, ONNX Runtime, edge runtimes
- Systems: real-time pipelines (vision, audio, language, action)
Focus
- Edge devices (Jetson, SoCs)
- Robotics & VLA systems
- Latency, stability, deployability
Philosophy
Optimization = model + runtime + system
models 22
vrfai/Qwen3-ASR-1.7B-int8
Automatic Speech Recognition • 2B • Updated • 3
vrfai/Qwen3-ASR-1.7B-int4
Automatic Speech Recognition • 2B • Updated • 3
vrfai/Qwen3-ASR-1.7B-fp8
Automatic Speech Recognition • 2B • Updated • 2.82k • 5
vrfai/Qwen3-ASR-1.7B-nvfp4
Automatic Speech Recognition • 1B • Updated • 193 • 5
vrfai/gemma-4-E4B-it-fp8
Text Generation • 8B • Updated • 2.56k • 4
vrfai/Qwen3.6-35B-A3B-NVFP4
Image-Text-to-Text • 34B • Updated • 546 • 3
vrfai/Qwen3.6-27B-FP8
Image-Text-to-Text • 27B • Updated • 2.15k • 2
vrfai/Qwen3.6-27B-NVFP4
Image-Text-to-Text • 19B • Updated • 11.3k • 6
vrfai/Cosmos-Reason2-8B-NVFP4
Image-Text-to-Text • 6B • Updated • 18.4k • 2
vrfai/Cosmos-Reason2-2B-NVFP4
Image-Text-to-Text • 2B • Updated • 205 • 2
datasets 0
None public yet