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.
PP
pplx embed v1 0.6b
Pplx · argus-ai
Params596M
Context32K
Q4_K_M0.4 GB
ET
ettin subject pairs 68m
Ettin · chartreuse-verte
Params68M
Context8K
Smallest0.1 GB
HI
Hippy AAI 7B
Hippy · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
BG
Bge Code v1
BGE · taylor-jones
Params1.54B
Context32K
Smallest1.6 GB
SO
Solon embeddings base 0.1
Solon · mradermacher
Params277M
Context512
Q4_K_M0.2 GB
HE
Heart RAG Embedder
Heart · mradermacher
Params23M
Context512
Q4_K_M0.0 GB
MI
nixie-querygen-v3
Mistral · nixiesearch
Params7.25B
Context32K
Smallest4.4 GB
MS
Msmarco Distilbert Cos v5
Msmarco · mradermacher
Params66M
Context512
Q4_K_M0.0 GB
EM
EmbeddingGemma-2 VQ
Embeddinggemma · Jlfn
Params392M
Context256K
Smallest0.4 GB
BG
hatedemics v1 bge v2 m3
BGE · mradermacher
Params568M
Context8K
Q4_K_M0.4 GB
MI
mistral embedded c instruct v0.4
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GT
Gte Reranker Modernbert Base
Gte · the-peoples-solutions
Params150M
Context8K
Smallest0.2 GB
BG
bge reranker v2 m3
BGE · tatsuyaaaaaaa
Params568M
Context8K
Q4_K_M0.4 GB
QW
Qwen3 VL Embedding 8B
Qwen · lainsoykaf
Params7.57B
Context256K
Q4_K_M4.7 GB
BG
bge reranker base Q4 K M
BGE · magicunicorn
Params278M
Context512
Q4_K_M0.2 GB
QW
Qwen3 Embedding 0.6B
Qwen · iyanello
Params596M
Context32K
Q4_K_M0.4 GB
KA
KaLM Reranker V1 Large
Kalm · KaLM-Embedding
Params7.09B
Context128K
Smallest7.5 GB
JI
jina embeddings v2 base en Q5 K M
Jina · djuna
Params137M
Context8K
Smallest0.1 GB
SN
bim wiki search
Snowflake · mikillicious
Params567M
Context8K
Smallest1.2 GB
RA
Rank_Vicuna_7B_V1_Fp16
Rank · tensorblock
Params6.74B
Context4K
Smallest2.5 GB
LL
Llm Embedder
Llm · mradermacher
Params109M
Context512
Q4_K_M0.1 GB
EM
embeddinggemma-GTAIDE-300m-2605
Embeddinggemma · phate334
Params308M
Context2K
Q4_K_M0.2 GB
QW
Qwen3 VL Embedding 8B
Qwen · Ganonook
Params7.57B
Context256K
Q4_K_M4.7 GB
BG
bge m3 Q4 K M
BGE · puppyM
Params567M
Context8K
Q4_K_M0.4 GB
LL
Llama 4 Maverick 17B 128E Instruct q8 with bf16 embedding and bf16 output
Llama · GeorgyGUF
Params401B
Context1024K
Smallest427.8 GB
MI
V2MiniLM SemanticEngine
Minilm · mradermacher
Params23M
Context512
Q4_K_M0.0 GB
EM
mindpage search v2
Embeddinggemma · Mindscend
Params271M
Context256K
Smallest0.3 GB
MI
MiniLM V6Data SemanticEngine
Minilm · mradermacher
Params23M
Context512
Q4_K_M0.0 GB
QW
Qwen3 Reranker 4B
Qwen · ebasKing
Params4.02B
Context40K
Q4_K_M2.5 GB
MU
Munche 768 Merged
Munche · senior5207
Params308M
Context2K
Q4_K_M0.2 GB