Embedding137M official

nomic-embed-text

by Nomic AI

English text embedding model with Matryoshka representation learning for resizable embeddings; requires task instruction prefixes.

#embedding #small

arcflare pull nomic-ai/nomic-embed-text-v1.5-GGUF:Q8_0

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

nomic-embed-text

English text embedding model with Matryoshka representation learning for resizable embeddings; requires task instruction prefixes.

Get it

arcflare pull nomic-ai/nomic-embed-text-v1.5-GGUF:Q8_0

arcflare run nomic-embed-text-v1.5

ArcFlare reads the GGUF header and loads it at the largest context your free VRAM can actually hold. Use arcflare fit to see that before downloading anything else, or arcflare use opencode to code with it.

Highlights

Downloads the Q8_0 file by default: 0.15 GB. Also published: Q4_K_M (0.08 GB), Q6_K (0.11 GB), f16 (0.27 GB)
Trained for a 8K context
Licence: Apache-2.0. Read it before commercial use

Sizes

137m · 0.15GB

Other sizes live in sibling repos: swap the size in the repo name when pulling.

[ 03 ] // relatedmore →

nomic-embed-text-v2-moe

Nomic AI

Embedding

Multilingual mixture-of-experts text embedding model (475M total, 305M active) supporting about 100 languages with Matryoshka embeddings.

size: 475M
vram: ~2 GB
license: Apache-2.0

8% of a 24 GB card

#embedding #small

embeddinggemma-300m

Google

Embedding

300M-parameter open embedding model from Google, built from Gemma 3 and trained on 100+ languages; 768-dim output with Matryoshka truncation.

size: 300M
vram: ~2 GB
license: Gemma

8% of a 24 GB card

#embedding #small

bge-m3

BAAI

Embedding

Multi-functionality, multilingual (100+ languages) and multi-granularity embedding model handling inputs up to 8192 tokens.

size: 568M
vram: ~2 GB
license: MIT

8% of a 24 GB card

#embedding #small