Mistral Small 4 Collection A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated 19 days ago • 63
inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-4.5bit Text Generation • 121B • Updated 22 days ago • 5.49k • 6
inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-9bit Text Generation • 121B • Updated 22 days ago • 6.17k • 6