Merino — unified embedding + reranker models - a baa-ai Collection

baa-ai 's Collections

Merino — unified embedding + reranker models

LTX-2.3 RAM Quantized (MLX)

Qwen3.6-35B-A3B

DeepSeek-V3.2 (MLX)

MiniMax-M2.7 (MLX)

Nemotron 3 Super

Qwen3.5-35B-A3B

Qwen3.5-122B-A10B

Qwen3.5-397B-A17B

Merino — unified embedding + reranker models

updated 28 days ago

One model for both halves of RAG retrieval; a strong default per size. Contact baa.ai for the optimal pick for your corpus.