System Configuration
Configure your hardware to check model compatibility
OpenVoice v2
AudioopenvoiceZero-shot cross-lingual voice cloning
XTTS-v2 Community
AudioxttsHighly downloaded open TTS with 6-second voice cloning
Qwen 3.5 0.8B
TextqwenMicro model for embedded devices
Qwen 3 TTS CustomVoice (1.7B)
Audioqwen-ttsHigh quality text to speech with voice cloning
Qwen 3.5 2B
TextqwenUltra-small edge model
Gemma-3n E2B IT
TextgemmaDeepMind instruction-tuned model for low-resource environments
Nanbeige 4.1 3B
TextnanbeigeEfficient Llama-based model
Fish TTS S2-Pro
Audiofish-ttsExpressive multilingual TTS trained on 10M+ hours of audio
StarCoder 2-3B
TextstarcoderSafe, permissively licensed coding model for local environments
Ministral 3 3B Instruct 2512
TextmistralMistral multimodal SLM targeting on-device agentic workflows
Phi-4 Mini Instruct
TextphiLightweight instruction-tuned SLM with 128k context
Qwen 3.5 4B
TextqwenSmall mobile-friendly model
Isaac GR00T N1
Roboticsgr00tNVIDIA humanoid foundation model
HumanPlus
RoboticshumanplusShadows human motion to robot
SwinIR
ImageswinirTransformer image restoration
Real-ESRGAN
ImageesrganImage super-resolution
Piper TTS
AudiopiperUltra-fast local TTS
YOLOv10
VisionyoloLatest YOLO model
BGE Small EN
EmbeddingbgeFast English embeddings
GFP-GAN
ImagegfpganFace restoration
Showing 20 of 531 models
VRAM Bottleneck Detected
Many models are running with RAM offloading. An upgrade to 16GB+ VRAM would significantly improve performance.
