Real World VoiceEQ Benchmark
🎙
22
Explore and compare speech model leaderboards with audio samples
Saw PrismML's Bonsai 27B 1-bit/ternary release. Curious about their core training/quantization methods vs Unsloth’s Dynamic Quant 2.0. Do you think Unsloth can reach similar uniform 1-bit/ternary performance?