hermitdave/Agnes-3.0-Flash-DWQ-4bit-MTP
Text Generation • 32B • Updated • 81
Distillation-Aware Weight Quantization
Distillation-Aware Weight Quant of models. The RTN is further trained using data generated from BF16 model or 8bit RTN quant if BF16 is not feasible.
-
-
hermitdave/LFM2.5-24B-A2B-MLX-DWQ-3bit-v2
Text Generation • 24B • Updated • 526 -
hermitdave/LFM2.5-24B-A2B-MLX-DWQ-3bit
Text Generation • 24B • Updated • 2.87k -
hermitdave/LFM2.5-24B-A2B-MLX-DWQ-4bit
Text Generation • 24B • Updated • 286 -
hermitdave/LFM2.5-24B-A2B-MLX-DWQ-4bit-v2
Text Generation • 24B • Updated • 163 -
hermitdave/LFM3-1.7B-MLX-DWQ-4bit
Text Generation • 2B • Updated • 116