Nemotron-3-Embed-1B-BF16-8bit
from nvidia/Nemotron-3-Embed-1B-BF16
Params
1.1B
Weights
≈ 1.2 GB
Mac memory
8 GB+
openmdw-1.1 · updated 2026-08-04
Apple silicon
Apple MLX models
5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 1h ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
3 builds · clear filters
Nemotron-3-Embed-1B-BF16
from nvidia/Nemotron-3-Embed-1B-BF16
Params
1.1B
Weights
≈ 2.3 GB
Mac memory
8 GB+
openmdw-1.1 · updated 2026-08-04
Nemotron-3-Embed-1B-BF16-4bit
from nvidia/Nemotron-3-Embed-1B-BF16
Params
1.1B
Weights
≈ 642 MB
Mac memory
8 GB+
openmdw-1.1 · updated 2026-08-04