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.

Most downloadedNewestLargestLongest contextSmallest
LF
LFM2.5 ColBERT 350M
Lfm · mradermacher
Params353M
Context125K
Q4_K_M0.2 GB
EmbeddingTool use
BG
Bge Large Zh v1.5
BGE · mradermacher
Params324M
Context512
Q4_K_M0.2 GB
Embedding
NO
NoInstruct Small Embedding v0
Noinstruct · mradermacher
Params33M
Context512
Q4_K_M0.0 GB
Embedding
WE
WeMM Embedding 9B
Wemm · seamon67
Params7.94B
Context256K
Smallest8.4 GB
EmbeddingReasoningTool use
MU
jp-music-title-encoder
Multilingual · gbnam8
Params40M
Context512
Smallest0.1 GB
CodingEmbedding
LE
Legal Embedding Ita 0.6B
Legal · mradermacher
Params596M
Context32K
Q4_K_M0.4 GB
EmbeddingReasoningTool use
MU
multilingual e5 base
Multilingual · cstr
Params277M
Context514
Smallest0.3 GB
Embedding
PP
pplx embed context v1 0.6b
Pplx · argus-ai
Params596M
Context32K
Q4_K_M0.4 GB
Embedding
RE
RenderRank 2B
Renderrank · mradermacher
Params1.72B
Context256K
Q4_K_M1.1 GB
EmbeddingTool useVision
JA
Jan Nano NoThinkEmbed Jan Chat
Jan · mradermacher
Params4.41B
Context40K
Q4_K_M2.7 GB
EmbeddingReasoningTool use
QW
gte-Qwen2-1.5B-instruct
Qwen · gaianet
Params1.78B
Context128K
Q4_K_M1.1 GB
CodingEmbedding
SM
e5-small-v2
Small · ChristianAzinn
Params33M
Context512
Q4_K_M0.0 GB
Embedding
QW
Qwen3-VL-Embedding-2B
Qwen · gorse-io
Params1.72B
Context256K
Q4_K_M1.1 GB
EmbeddingTool useVision
MI
Mistral 7B Merge 14 v0.3
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
Embedding
BE
bekko embedding v1 a25m
Bekko · hotchpotch
Params123M
Context8K
Smallest0.1 GB
Embedding
GE
BAAI bge reranker v2 gemma
Gemma · RichardErkhov
Params2.51B
Context8K
Q4_K_M1.6 GB
Embedding
MX
Mxbai Rerank Large v2
Mxbai · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
EmbeddingTool use
ML
ML E5 0.6B
mradermacher
Params559M
Context512
Q4_K_M0.4 GB
Embedding
QW
Qwen3 Reranker 8B
Qwen · xentauri
Params8.19B
Context40K
Q4_K_M5.0 GB
EmbeddingReasoningTool use
QW
Mursit Embed Qwen3 4B TR
Qwen · mradermacher
Params4.02B
Context40K
Q4_K_M2.5 GB
CodingEmbeddingReasoning
SE
semantic lite
Semantic · ukung
Params250M
Context40K
Smallest0.2 GB
Embedding
BE
bekko embedding v1 a8m
Bekko · hotchpotch
Params106M
Context8K
Smallest0.1 GB
Embedding
MI
Mistral 7B Merge 14 v0.1 Mistral 7B Instruct v0.1
Mistral · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
Embedding
EM
embeddinggemma 300m
Embeddinggemma · cstr
Params308M
Context2K
Smallest0.3 GB
Embedding
DA
Daredevil 7B
Daredevil · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
Embedding
BY
ByteGPT r1
Bytegpt · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
EmbeddingReasoningTool use
BE
bekko embedding v1 a25m
Bekko · leok7v
Params123M
Context8K
Smallest0.1 GB
Embedding
BG
bge-large-en-v1.5
BGE · ChristianAzinn
Params334M
Context512
Q4_K_M0.2 GB
Embedding
QW
Qwen3 Embedding Medical 0.6B
Qwen · lastmass
Params596M
Context32K
Smallest1.2 GB
EmbeddingReasoningTool use
QW
Qwen2 1.5b
Qwen · mradermacher
Params1.54B
Context128K
Q4_K_M1.0 GB
Embedding

Other uses

Keep browsing