nvidia/Nemotron-3-Embed-1B-BF16
Quantization vs mistralai/Ministral-3-3B-Instruct-2512. mistralai/Ministral-3-3B-Instruct-2512 is a quantized version of the other (F8_E4M3/BF16).
11 derivatives checked
- zenmagnets/Nemotron-3-Embed-1B-Q4_K_M-GGUF: Quantization
- nvidia/Nemotron-3-Embed-1B-NVFP4: Quantization
- groxaxo/Nemotron-3-Embed-1B-AWQ-W4A16: Quantization
- nanoandrew4/Nemotron-3-Embed-1B-GGUF: Same weights, converted
- NeoRoth/nemotron-3-embed-1b-gguf: Same weights, converted
- mlx-community/Nemotron-3-Embed-1B-BF16-8bit: Quantization
- mlx-community/Nemotron-3-Embed-1B-BF16-4bit: Quantization
- KIEFERSA/Sophea-Nemo-Embedding: Full fine-tune
- mlx-community/Nemotron-3-Embed-1B-BF16: Same weights, repacked
- malteos/most-embed-de: Partial fine-tune
- groxaxo/Nemotron-3-Embed-1B-oQ6-MLX: Quantization
2 other repos hold byte-for-byte identical weight files.