Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion Paper • 2605.12825 • Published 20 days ago • 12
nvidia/parakeet-tdt-0.6b-v3 Automatic Speech Recognition • 0.6B • Updated 11 days ago • 64.2k • • 886
APEX Quants (GGUF) Collection MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 36 items • Updated 2 days ago • 104