Models

Models on Hugging Face

5 public models under huggingface.co/cavi-ai (opens in new tab), listed from the Hub as of Nov 14, 2026. Each model card states its measured results, requirements and license.

All models

CAVI-AI models on Hugging Face
ModelTaskBase modelFormatSizeDownloads, 30 daysDownload
Qwen3-VL-8B-Instruct-MLX-4bit (opens in new tab)Apache-2.0 weightsVision-languageQwen/Qwen3-VL-8B-Instruct (opens in new tab)MLX 4-bit5.78 GB127hf download cavi-ai/Qwen3-VL-8B-Instruct-MLX-4bit
bobby-control-detector (opens in new tab)Apache-2.0 weightsObject detectionPekingU/rtdetr_v2_r18vd (opens in new tab)safetensors + ONNX0.16 GB58hf download cavi-ai/bobby-control-detector
Audio8-ASR-Infinite-MLX-8bit (opens in new tab)Apache-2.0 weights · MIT codeSpeech recognitionEdge0/Audio8-ASR-Infinite (opens in new tab)MLX 8-bit5.29 GB48hf download cavi-ai/Audio8-ASR-Infinite-MLX-8bit
Audio8-ASR-Infinite-MLX-4bit (opens in new tab)Apache-2.0 weights · MIT codeSpeech recognitionEdge0/Audio8-ASR-Infinite (opens in new tab)MLX 4-bit3.75 GB38hf download cavi-ai/Audio8-ASR-Infinite-MLX-4bit
laya-MLX-8bit (opens in new tab)Apache-2.0 weights · MIT codeText classificationconvaiinnovations/laya (opens in new tab)MLX 8-bit1.62 GB500hf download cavi-ai/laya-MLX-8bit

Run them on your Mac

Measured results on an Apple M5 Max for each MLX conversion are on the local models page.