Embedding GGUF models
2342 GGUF models: embedding models for search and RAG. Sizes run from 1M to 671B parameters. The longest trained context is 1024K tokens.
MX
Mxbai Rerank Large v2
Mxbai · pyarn
Params1.54B
Context32K
Smallest1.6 GB
QW
Qwen2.5 0.5B Reasoning Embedding
Qwen · wahidmounir
Params494M
Context32K
Smallest0.5 GB
FA
Facebook Dpr Ctx_Encoder Multiset Base
Facebook · mradermacher
Params109M
Context512
Q4_K_M0.1 GB
OP
openPangu Embedded 1B V1.1
Openpangu · Lpzhan
Params1.16B
Context32K
Smallest2.3 GB
NO
Nomic Embed Text v1.5
Nomic · RinaChen
Params137M
Context2K
Q4_K_M0.1 GB
BG
Fin Bge v1
BGE · mradermacher
Params109M
Context512
Q4_K_M0.1 GB
QW
Qwen3 Reranker 8B
Qwen · endyjasmi
Params7.57B
Context40K
Q4_K_M4.7 GB
SN
Snowflake Arctic Embed L v2.0
Snowflake · Savyasaachin
Params567M
Context8K
Smallest0.6 GB
GR
Granite Embedding Small English R2
Granite · sanjanasrikanth
Params48M
Context8K
Smallest0.1 GB
BG
BAAI/bge-m3
BGE · AmpereComputing
Params567M
Context8K
Smallest0.5 GB
QW
Qwen3 Reranker 0.6B
Qwen · novelaide
Params596M
Context40K
Smallest0.6 GB
ME
medical 20 0 16 jinaai jina embeddings v2 small en 1000 gpt 4 turbo 01 9062874564
Medical · mradermacher
Params32M
Context8K
Q4_K_M0.0 GB
BG
Bge Large En v1.5
BGE · sabafallah
Params334M
Context512
Smallest0.4 GB
QW
Qwen2 VL 72B Instruct q8 with bf16 output and bf16 embedding
Qwen · GeorgyGUF
Params72.7B
Context32K
Smallest79.6 GB
NO
Nomic Embed Text v1.5
Nomic · BenevolenceMessiah
Params137M
Context2K
Smallest0.1 GB
QW
Qwen3 VL Embedding 2B
Qwen · turingevo
Params1.72B
Context256K
Q4_K_M1.1 GB
QW
Qwen3 Reranker 8B
Qwen · camelliah
Params8.19B
Context40K
Q4_K_M5.0 GB
QW
Qwen3 Embedding 8B GGUF IQ4 XS
Qwen · majentik
Params7.57B
Context40K
Smallest4.3 GB
CH
Chuxin Embedding Q8 0
Chuxin · lagoon999
Params567M
Context8K
Smallest0.6 GB
JI
jina embeddings v2 base en Q8 0
Jina · sarav1n
Params137M
Context8K
Smallest0.1 GB
QW
Qwen3 Embedding 0.6b
Qwen · AIconjured
Params596M
Context32K
Smallest0.5 GB
LL
F2LLM V2 1.7B
Llm · seamon67
Params1.72B
Context40K
Smallest1.8 GB
AL
all-MiniLM-L6-v2
All · Jarbas
Params23M
Context512
Q4_K_M0.0 GB
MU
multilingual e5 base Q5 0
Multilingual · jeremyys
Params277M
Context512
Smallest0.2 GB
QW
Gte Qwen2 7B Instruct
Qwen · soichisumi
Params7.61B
Context128K
Smallest8.1 GB
BG
bge m3 doc r2.1
BGE · keisuke-miyako
Params567M
Context8K
Smallest0.6 GB
ET
ettin povtense 17m v2
Ettin · chartreuse-verte
Params17M
Context8K
Smallest0.0 GB
QW
Qwen3 Embedding 0.6B
Qwen · AXONVERTEX-AI-RESEARCH
Params596M
Context32K
Smallest0.6 GB
QW
Qwen3 Embedding 0.6B deik finetune
Qwen · SMARTICT
Params596M
Context32K
Q4_K_M0.4 GB
RA
rank1 7b
Rank · tensorblock
Params7.62B
Context128K
Smallest3.0 GB