Running Agents 24 Real World VoiceEQ Benchmark π 24 Explore and compare speech model leaderboards with audio samples
google/diffusiongemma-26B-A4B-it Image-Text-to-Text β’ 26B β’ Updated 11 days ago β’ 1.77M β’ 1.15k
nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps Feature Extraction β’ Updated Aug 30, 2025 β’ 1.39k β’ 19
unsloth/diffusiongemma-26B-A4B-it-GGUF Image-Text-to-Text β’ 25B β’ Updated 22 days ago β’ 80.8k β’ 369
Running Featured 473 HF Realtime Voice π 473 Voice chat over WebSocket against a HF speech-to-speech
Running on Zero Agents Featured 116 Gemma 4 12B IT β‘ 116 Chat with an AI using text, images, audio, or video
empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF Image-Text-to-Text β’ 9B β’ Updated 12 days ago β’ 1.57M β’ 2.47k