LOCAL_AI_STACK
v2.2 · 2026-06-12
← back to models

Nomic Embed Text v1.5

nomic-embed-text
EMBEDDING

Nomic Embed Text v1.5 is a 0.137B embedding model profile for local AI planning. This page records provider, license, context, quantization, hardware-fit estimates, setup hints, source links, and caveats so readers do not choose a model by name alone.

PROVIDER
Nomic AI
FAMILY
Nomic Embed
MODEL TYPE
embedding
PARAMETERS
0.137B
MODALITIES
text
ARCHITECTURE
nomic-bert encoder
CONTEXT WINDOW
8,192 tokens
TRAINING TOKENS
—
RELEASE DATE
2024-02-14
LICENSE & LINKS
GGUF REPOSITORIES
Official Nomic GGUF repository; file table provides quantization sizes and embedding MSE versus the Sentence Transformers implementation.
SETUP HINTS
OLLAMA
Use `ollama pull nomic-embed-text`, then call Ollama's embeddings endpoint with model `nomic-embed-text`.
LM STUDIO
Use it as an embedding model, not chat
LLAMA.CPP
Use the llama.cpp `embedding` example with the official GGUF
QUANTIZATION FILE SIZES (GGUF)
Q4_K_M
0.084 GB
Q5_K_M
0.1 GB
Q8_0
0.146 GB
Quantization note: Q5_K_M for small local footprint with low embedding MSE; Q8_0 for maximum quantized fidelity
RAM / VRAM ESTIMATES
MIN RAM
1 GB
COMFORTABLE RAM
2 GB
These are conservative local-inference estimates, not official hardware requirements.
HARDWARE FIT
CPU only (no GPU)
good
8 GB RAM
good
16 GB RAM
good
32 GB RAM
good
8 GB VRAM
good
12 GB VRAM
good
24 GB VRAM
good
Apple Silicon (unified memory)
good
Hardware fit values are conservative local-inference estimates based on GGUF size plus runtime and KV-cache overhead. Actual requirements depend on context length, quantization, runtime, GPU offload, and other running apps.
BEST FOR
·Small local English embedding model for RAG, similarity search, clustering, and classification
AVOID IF
·You need multilingual retrieval as a primary requirement.
CAVEATS
·This is an embedding model only; it cannot generate chat responses.
·Ollama's library page lists a 2K context window for its packaged model, while the Nomic model card/docs list 8192 tokens; use runtime-specific behavior for catalog UI warnings.
SOURCE URLS
FIELD EVIDENCE
LANGUAGES
English
CAPABILITIES
embedding model
← BGE-M3Gemma 2 2B Instruct →