nomic-embed-text
Partner VerifiedPublisher: Nomic AI · Category: Embedding
Parameters
137M
Context Window
8K
Default Size
274 MB
Downloads
640,000
High-performance text embedding model for RAG semantic search and vector database indexing.
PULL MODEL
eq pull nomic-embed-text
RUN INFERENCE
eq run nomic-embed-text "Generate vector embedding for document"
Attention Architecture
Utilizes Grouped-Query Attention (GQA) with 16-token fixed Paged KV Cache block allocation for zero-fragmentation memory residency.
ONNX & EQC Compatible
Compiles directly through the EQC toolchain into standalone .eqx binary packages with fused SwiGLU kernels.
Multi-Hardware Support
Auto-detects CUDA RTX/A100/H100, Apple Silicon Metal Performance Shaders, or AVX-512 CPU execution backends.