Nemotron 3 MLX Quantizations

DreamFoundries 's Collections

updated Jun 29

MLX-LM affine quantizations for Nemotron 3; see each model card for details.

DreamFoundries/NVIDIA-Nemotron-3-Super-120B-A12B-BF16-4bit

Text Generation • 121B • Updated Jun 29 • 85

Note 4-bit MLX-LM affine quantization of nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16. No comparative benchmarks yet.
DreamFoundries/NVIDIA-Nemotron-3-Super-120B-A12B-BF16-6bit

Text Generation • 121B • Updated Jun 29 • 93

Note 6-bit MLX-LM affine quantization of nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16. No comparative benchmarks yet.
DreamFoundries/NVIDIA-Nemotron-3-Super-120B-A12B-BF16-8bit

Text Generation • 121B • Updated Jun 29 • 93

Note 8-bit MLX-LM affine quantization of nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16. No comparative benchmarks yet.
DreamFoundries/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-4bit

Text Generation • 32B • Updated Jun 29 • 28

Note 4-bit MLX-LM affine quantization of nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16. No comparative benchmarks yet.
DreamFoundries/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-6bit

Text Generation • 32B • Updated Jun 29 • 29

Note 6-bit MLX-LM affine quantization of nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16. No comparative benchmarks yet.
DreamFoundries/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-8bit

Text Generation • 32B • Updated Jun 29 • 40

Note 8-bit MLX-LM affine quantization of nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16. No comparative benchmarks yet.