lmstudio-community/Qwen3-4B-Thinking-2507-MLX-8bit Text Generation • 4B • Updated Aug 6, 2025 • 48.9k • 8
meta-llama/Llama-4-Scout-17B-16E-Instruct Image-Text-to-Text • 109B • Updated May 22, 2025 • 159k • • 1.35k
Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-MLX_8bit Text Generation • 2B • Updated Nov 26, 2024 • 65 • 8