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.
MA
ms marco TinyBERT L6 Q8 0
Marco · sinjab
Params66M
Context512
Smallest0.1 GB
RO
roberta cnn legal Q8 0
Roberta · Sleem247
Params354M
Context512
Smallest0.4 GB
BG
bge m3 doc r2
BGE · keisuke-miyako
Params567M
Context8K
Smallest0.6 GB
QW
Qwen3 Reranker 8B
Qwen · G17c21ds
Params7.57B
Context40K
Smallest3.1 GB
MX
mxbai embed xsmall v1 Q8 0
Mxbai · twine-network
Params24M
Context4K
Smallest0.0 GB
CT
ctxl rerank v2 instruct multilingual 1b gguf q4 k m
Ctxl · keisuke-miyako
Params1.33B
Context40K
Q4_K_M0.9 GB
LY
Lychee Embed
Lychee · fastfalcon79
Params1.54B
Context32K
Smallest0.7 GB
LY
Lychee Embed
Lychee · fastfalcon79
Params1.54B
Context32K
Q4_K_M1.0 GB
NE
nvidia/Nemotron-3-Embed-1B-BF16
Nemotron · ldov
Params14.8B
Context256K
Q4_K_M0.7 GB
GT
Gte Base
Gte · sizzlebop
Params109M
Context512
Q4_K_M0.1 GB
QW
Qwen3 Reranker 8B
Qwen · k0zmik
Params8.19B
Context40K
Smallest8.7 GB
BG
bge reranker v2 m3 Q8 0
BGE · amon-epa
Params568M
Context8K
Smallest0.6 GB
QW
Qwen3 Reranker 8B
Qwen · FukayaTakashi
Params8.19B
Context40K
Q4_K_M5.0 GB
BG
bge reranker base gguf q8 0
BGE · keisuke-miyako
Params278M
Context512
Smallest0.3 GB
CT
ctxl rerank v2 instruct multilingual 1b gguf q8 0
Ctxl · keisuke-miyako
Params1.33B
Context40K
Smallest1.4 GB
SN
Snowflake Arctic Embed S
Snowflake · yixuan-chia
Params33M
Context512
Smallest0.0 GB
QW
Gte Qwen2 7B Instruct
Qwen · Nizzouuu
Params7.61B
Context128K
Smallest6.3 GB
AR
arctic embed xs GGUF Q4 K M
Arctic · kamranjon
Params23M
Context512
Q4_K_M0.0 GB
AL
all MiniLM L6 v2 Q6 K
All · nesall
Params23M
Context512
Smallest0.0 GB
QW
Qwen3 VL Reranker 2B
Qwen · staralt
Params1.72B
Context256K
Smallest1.1 GB
BG
bge m3 legal euro r8
BGE · keisuke-miyako
Params567M
Context8K
Smallest0.6 GB
BG
bge m3 legal euro r13
BGE · keisuke-miyako
Params567M
Context8K
Smallest0.6 GB
LY
Lychee Embed
Lychee · TensorVizion
Params1.54B
Context32K
Smallest0.7 GB
ST
stella-base-zh-v2
Stella · wencan-lab
Params102M
Context1K
Q4_K_M0.1 GB
IT
ItaLegalEmb v2
Italegalemb · Kleva-ai
Params567M
Context8K
Smallest0.6 GB
MU
multilingual e5 large Q8 0
Multilingual · apto-as
Params559M
Context512
Smallest0.6 GB
NO
nomic-embed-text-v1.5
Nomic · Inza124
Params137M
Context2K
Smallest0.3 GB
LA
E5 Large Korean
Large · Nagase-Kotono
Params559M
Context512
Smallest0.6 GB
BG
Bge Reranker v2 M3
BGE · ragbox
Params568M
Context8K
Smallest0.6 GB
AL
all MiniLM L12 v2 Q8 0
All · badger212
Params33M
Context512
Smallest0.0 GB