prism-ml/Bonsai-27B-mlx-1bit
Quantization vs Qwen/Qwen3.6-27B. prism-ml/Bonsai-27B-mlx-1bit is a quantized version of the other (U32/F16).
4 derivatives checked
- VertexAIco/Bonsai-27b-MLX-UltraFastUnStable: Same weights, repacked
- VertexAIco/Bonsai-27b-MLX-Fast: Same weights, repacked
- ZakuroAI/Bonsai-27B-mlx-1bit-vision4bit: Same weights, repacked
- VertexAIco/Bonsai-27b-MLX-Optimization: Identical copy
6 other repos hold byte-for-byte identical weight files.