moonshotai/Kimi-K3
Image-Text-to-Text • 2.8T • Updated • 99.2k • • 8.63k
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?