nvidia/Nemotron-3-Embed-8B-BF16
Quantization vs mistralai/Ministral-3-8B-Instruct-2512. mistralai/Ministral-3-8B-Instruct-2512 is a quantized version of the other (F8_E4M3/BF16).
9 derivatives checked
- Abiray/Nemotron-3-Embed-8B-GGUF: Quantization
- Aqua00/Nemotron-3-Embed-8B-GGUF: Same weights, converted
- groxaxo/Nemotron-3-Embed-8B-AWQ-W4A16-G32-ASYM: Quantization
- shadowrock-io/Nemotron-3-Embed-8B-Community-NVFP4: Quantization
- shadowrock-io/Nemotron-3-Embed-8B-Community-MLX-4bit: Quantization
- minetta/nemotron-3-embed-8b-legal: LoRA-style
- shadowrock-io/Nemotron-3-Embed-8B-Community-FP8: Quantization
- Hanno-Labs/dinghy-law-8b-v1: LoRA-style
- ibrahimkettaneh/Nemotron-3-Embed-8B-NVFP4-ModelOpt-PTQ-Experimental: Quantization
4 other repos hold byte-for-byte identical weight files.