lmstudio-community/Qwen3-4B-Thinking-2507-MLX-8bit Text Generation • 1B • Updated Aug 6, 2025 • 53k • 7
Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-MLX_8bit Text Generation • 0.4B • Updated Nov 26, 2024 • 85 • 8