shadowrock-io/Nemotron-3-Embed-8B-Community-FP8
Sentence Similarity • 8B • Updated • 7.61k • 1
Nemotron-3-Embed-8B Community Quantizations
FP8, NVFP4 (Blackwell), and MLX 4-bit builds — validated on RTEB-open within 0.008 nDCG@10 of NVIDIA's published scores.
Note FP8 W8A8 for Ada/Hopper/Blackwell; within 0.008 nDCG@10 of published RTEB scores.
shadowrock-io/Nemotron-3-Embed-8B-Community-NVFP4
Sentence Similarity • 5B • Updated • 335 • 2Note Blackwell-native 4-bit.
shadowrock-io/Nemotron-3-Embed-8B-Community-MLX-4bit
Sentence Similarity • 1B • Updated • 289 • 1Note Apple Silicon (MLX) 4-bit.
nvidia/Nemotron-3-Embed-8B-BF16
Sentence Similarity • 8B • Updated • 112k • 91Note Upstream BF16 base model.