Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ6
Mixed-precision quantization for Apple Silicon, text-only mode (vision tower stripped). Recommended text-only version — best quality-to-size ratio. Quantized...
Метка: oq6
Qwen3.6-35B-A3B-oQ6
— Quantization: oQ6 (sensitivity-driven mixed precision, groupsize=64) — Format: MLX safetensors — Compatible with:** mlx-lm, mlx-vlm, oMLX on...