BGE GGUF models

296 GGUF models in the BGE family, quantized by 142 uploaders. Sizes run from 17M to 30.5B parameters. The longest trained context is 125K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
BG
bge small en v1.5
BGE · unsloth
Params33M
Context512
Smallest0.1 GB
Embedding
BG
bge-small-en-v1.5
BGE · CompendiumLabs
Params33M
Context512
Q4_K_M0.0 GB
Embedding
BG
bge-large-en-v1.5
BGE · CompendiumLabs
Params334M
Context512
Q4_K_M0.2 GB
Embedding
BG
bge-base-en-v1.5
BGE · CompendiumLabs
Params109M
Context512
Q4_K_M0.1 GB
Embedding
BG
bge m3
BGE · gpustack
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
BG
bge reranker v2 m3
BGE · gpustack
Params568M
Context8K
Q4_K_M0.4 GB
Embedding
BG
bge m3 Q8 0
BGE · ggml-org
Params567M
Context8K
Smallest0.6 GB
Embedding
BG
bge-small-zh-v1.5
BGE · CompendiumLabs
Params24M
Context512
Q4_K_M0.0 GB
Embedding
BG
bge m3
BGE · lm-kit
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
BG
Bge Small En v1.5
BGE · ggml-org
Params33M
Context512
Smallest0.0 GB
Embedding
BG
bge m3
BGE · CompendiumLabs
Params567M
Context8K
Smallest1.2 GB
Embedding
BG
bge-small-en-v1.5
BGE · ChristianAzinn
Params33M
Context512
Q4_K_M0.0 GB
Embedding
BG
bge m3
BGE · vonjack
Params567M
Context8K
Smallest0.6 GB
Embedding
BG
bge m3
BGE · bbvch-ai
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
BG
bge large en i1
BGE · mradermacher
Params334M
Context512
Q4_K_M0.2 GB
Embedding
BG
bge reranker base Q4 K M
BGE · sabafallah
Params278M
Context512
Q4_K_M0.2 GB
Embedding
BG
bge m3
BGE · cstr
Params567M
Context8K
Smallest0.4 GB
Embedding
BG
Motherlode Code Small En v0.1
BGE · RiverRider
Params33M
Context512
Smallest0.1 GB
CodingEmbedding
BG
bge large zh i1
BGE · mradermacher
Params324M
Context512
Q4_K_M0.2 GB
Embedding
BG
bge m3
BGE · KimChen
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
BG
bge-large-zh-v1.5
BGE · CompendiumLabs
Params324M
Context512
Q4_K_M0.2 GB
Embedding
BG
baai bge reranker v2 m3 m3
BGE · cPilotGod
Params568M
Context8K
Q4_K_M0.4 GB
Embedding
BG
bge reranker v2 m3
BGE · cstr
Params568M
Context—
Smallest0.5 GB
GGUF
BG
bge reranker base
BGE · cstr
Params278M
Context—
Smallest0.3 GB
GGUF
BG
BGE_M3_Mindspore
BGE · mradermacher
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
BG
bge reranker v2 m3 Q8 0
BGE · pqnet
Params568M
Context8K
Smallest0.6 GB
Embedding
BG
bge-base-zh-v1.5
BGE · CompendiumLabs
Params102M
Context512
Q4_K_M0.1 GB
Embedding
BG
bge reranker v2 m3
BGE · smarttasks
Params568M
Context8K
Q4_K_M0.4 GB
CodingEmbedding
BG
baai bge m3 568m
BGE · cPilotGod
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
BG
bge m3
BGE · smarttasks
Params567M
Context8K
Q4_K_M0.4 GB
Embedding

About the BGE GGUF models

BGE is represented on ggufmodels.com by 296 GGUF models, quantized by 142 uploaders on Hugging Face. The most downloaded are bge small en v1.5, bge-small-en-v1.5 and bge-large-en-v1.5. Parameter counts run from 17M to 30.5B, and the longest trained context window is 125K tokens.

A Q4_K_M file of a BGE model is between 0.0 to 5.0 GB, which is the quant most people start with. Most files come from keisuke-miyako (42), mradermacher (39) and sinjab (9). The quants you will meet most often are Q8_0 (177), Q4_K_M (133), Q5_K_M (70) and F16 (66), where the number is how many models offer that quant.

Frequently asked questions

Which BGE GGUF should I download?

The most downloaded BGE GGUF here is bge small en v1.5. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a BGE model need?

Q4_K_M files of BGE models on this site range from 0.0 to 5.0 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do BGE GGUF files come from?

The most common quantizers here are keisuke-miyako, mradermacher and sinjab. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing