NVIDIA Nemotron 3.5 Bolt E4B in 5 imatrix-calibrated MLX sizes (3–8 bit) for Apple Silicon. Model by NVIDIA; quantized by Uraion Labs.
-
nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16
Text Generation • 8B • Updated • 4.19k • 58 -
nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16-DFlash-NVFP4
Text Generation • 0.5B • Updated • 497 • 7 -
UraionLabs/NVIDIA-Nemotron-3.5-Bolt-E4B-MLX-oQ4e
Text Generation • 9B • Updated • 145 • 1 -
UraionLabs/NVIDIA-Nemotron-3.5-Bolt-E4B-MLX-oQ8e
Text Generation • 8B • Updated • 150 • 1