EgorKodin/Qwen3.8-27B-ABLITERATED-3bit-MLX-TextOnly

Quantization vs Blackfrost-AI/Qwen3.8-27B-ABLITERATED-BF16. EgorKodin/Qwen3.8-27B-ABLITERATED-3bit-MLX-TextOnly is a quantized version of the other (U32/BF16).

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse