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.
AL
all MiniLM L6 v2 Q4 K M
All · fartboner
Params23M
Context512
Q4_K_M0.0 GB
BG
bge m3 gguf q4 k m
BGE · keisuke-miyako
Params567M
Context8K
Q4_K_M0.4 GB
QW
Qwen3 Embedding 4B
Qwen · mosama
Params4.02B
Context40K
Q4_K_M2.5 GB
QW
Qwen3 Embedding 8B
Qwen · Srijan-Chakraborty
Params7.57B
Context40K
Smallest8.0 GB
AL
all MiniLM L6 v2 f16
All · embedme
Params23M
Context512
Smallest0.0 GB
SN
snowflake arctic embed m long
Snowflake · keisuke-miyako
Params137M
Context2K
Smallest0.1 GB
QW
Qwen3 Reranker 0.6B
Qwen · Chiwei
Params596M
Context40K
Smallest0.6 GB
QW
Qwen3K
Qwen · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
SN
Snowflake Arctic Embed M v1.5
Snowflake · sheldonrobinson
Params109M
Context512
Smallest0.1 GB
QW
Qwen3 Reranker 4B
Qwen · pyarn
Params4.02B
Context40K
Smallest4.3 GB
MI
Mistral 7B Merge 14 v0.3 Ft Step 9984
Mistral · RichardErkhov
Params7.24B
Context32K
Smallest2.7 GB
LL
Llama 3 1 Nemotron 51B Instruct Q3 K S with q6 K output and embed and blk.70 79.attn out
Llama · GeorgyGUF
Params51.5B
Context128K
Smallest23.3 GB
JI
Jina Embeddings v3
Jina · rockon1095
Params558M
Context8K
Smallest0.4 GB
MX
Mxbai Rerank Base v2
Mxbai · keisuke-miyako
Params494M
Context32K
Q4_K_M0.4 GB
QW
gte-Qwen2-7B-instruct
Qwen · niancheng
Params7.61B
Context128K
Q4_K_M4.7 GB
QW
Qwen3 Reranker 4B
Qwen · Chiwei
Params4.02B
Context40K
Smallest2.4 GB
MA
ms marco MiniLM L2 v2 F16
Marco · sinjab
Params16M
Context512
Smallest0.0 GB
GR
granite embedding reranker english r2 gguf q4 k m
Granite · keisuke-miyako
Params150M
Context8K
Q4_K_M0.1 GB
MX
Mxbai Embed Large v1
Mxbai · smarttasks
Params334M
Context512
Q4_K_M0.2 GB
QW
Qwen3 Embedding 0.6B
Qwen · kerncore
Params596M
Context32K
Q4_K_M0.4 GB
LL
EmbeddedWiki Llama 3.1 70B Instruct
Llama · Ugljesa
Params70.6B
Context128K
Q4_K_M42.5 GB
MA
MAI DS R1 q8 with bf16 embedding and bf16 output
Mai · GeorgyGUF
Params671B
Context160K
Smallest715.0 GB
MA
ms marco TinyBERT L2 Q4 K M
Marco · sinjab
Params4M
Context512
Q4_K_M0.0 GB
JI
Jina Reranker v2 Base Multilingual
Jina · keisuke-miyako
Params278M
Context1K
Q4_K_M0.2 GB
GR
granite embedding reranker english r2 gguf q8 0
Granite · keisuke-miyako
Params150M
Context8K
Smallest0.2 GB
QW
gte-Qwen2-1.5B-instruct
Qwen · msyukorai
Params1.78B
Context128K
Smallest1.0 GB
NO
nomic-embed-text-v1.5
Nomic · v8karlo
Params137M
Context2K
Smallest0.1 GB
GR
Granite Embedding 30m English
Granite · r0x0d
Params30M
Context512
Q4_K_M0.0 GB
SI
SiriusOpen Beta02 2b
Siriusopen · Jace99
Params2.61B
Context8K
Smallest1.6 GB
OP
OpenScholar Reranker Q4 K M
Openscholar · Muthukumaran
Params560M
Context512
Q4_K_M0.4 GB