q2 · vlm
Ternary Bonsai 27B (2-bit)
prism-ml
Ternary-weight compression of Qwen3.6 27B, for text generation with optional image input.
◆ huggingface.co
details →
mlx models.
sourced.
ready to run.
Converted and quantized weights for Apple Silicon. Every entry links straight back to the repo it came from.