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 L2 F16
Marco · sinjab
Params4M
Context512
Smallest0.0 GB
QW
Gme Qwen2 VL 7B Instruct
Qwen · CCwz
Params7.62B
Context32K
Smallest5.3 GB
TE
test embed
Test · Shay1309
Params3.61B
Context128K
Smallest3.8 GB
BG
bge m3 Q4 K M
BGE · stefancosma
Params567M
Context8K
Q4_K_M0.4 GB
QW
Qwen3 Reranker 8B
Qwen · G17c21ds
Params7.57B
Context40K
Smallest8.0 GB
HO
Hourai2 50m Embedding
Hourai · WariHima
Params28M
Context32K
Q4_K_M0.0 GB
GE
bge reranker v2 gemma Q8 0
Gemma · Savyasaachin
Params2.51B
Context8K
Smallest2.7 GB
QW
Qwen3 Reranker 0.6B
Qwen · fuckoff11
Params596M
Context40K
Q4_K_M0.4 GB
BG
bge base en
BGE · mradermacher
Params109M
Context512
Q4_K_M0.1 GB
LA
lightonai lateon code edge f16
Lateon · embedme
Params17M
Context8K
Smallest0.0 GB
RU
Ruri v3 310m
Ruri · Targoyle
Params315M
Context8K
Q4_K_M0.2 GB
GE
bge reranker v2 gemma Q4 K M
Gemma · walsons
Params2.51B
Context8K
Q4_K_M1.6 GB
CO
CodeR Full
Coder · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
QW
Qwen3 Reranker 0.6B
Qwen · yeahbeen
Params596M
Context40K
Smallest0.6 GB
BG
bge m3 lemur r1
BGE · keisuke-miyako
Params567M
Context8K
Smallest0.6 GB
MA
ms marco MiniLM L6 v2 Q4 K M
Marco · sinjab
Params23M
Context512
Q4_K_M0.0 GB
QW
Gte Qwen2 7B Instruct
Qwen · redshiva
Params7.61B
Context128K
Smallest8.1 GB
AE
AeroEmbed 1
Aeroembed · AeroAIAviation
Params752M
Context256K
Q4_K_M0.5 GB
QW
Qwen3 Reranker 4B
Qwen · americansquid
Params4.02B
Context40K
Q4_K_M2.5 GB
NO
nomic embed text v2 moe GGUF IQ4 XS
Nomic · majentik
Params475M
Context2K
Smallest0.3 GB
EM
Embeddinggemma 300M Qat Q4_0 Unquantized
Embeddinggemma · empyrealworks
Params303M
Context2K
Smallest0.3 GB
MX
Mxbai Embed Large v1
Mxbai · smcleod
Params334M
Context512
Smallest0.4 GB
BG
bge reranker base Q8 0
BGE · magicunicorn
Params278M
Context512
Smallest0.3 GB
AL
mini embedding lora
All · jaswanthsanjay88
Params23M
Context512
Smallest0.0 GB
GR
granite embedding english r2 gguf q8 0
Granite · keisuke-miyako
Params149M
Context8K
Smallest0.2 GB
BG
German RAG BGE M3 MERGED x SNOWFLAKE ARCTIC HESSIAN AI Q8 0
BGE · avemio
Params567M
Context8K
Smallest0.6 GB
QW
Qwen3 Embedding 4B GGUF IQ4 XS
Qwen · majentik
Params4.02B
Context40K
Smallest2.3 GB
QW
Qwen3 Embedding 0.6B
Qwen · CablepunkPress
Params596M
Context32K
Smallest0.6 GB
MI
MicroLlama text embedding Q4 K M
Microllama · Amine-Mike
Params272M
Context2K
Q4_K_M0.2 GB
JA
Jan Nano NoThinkEmbed
Jan · DESUCLUB
Params4.41B
Context40K
Smallest2.5 GB