---

jina-embeddings-v2-base-zh-GGUF

Original Model

jinaai/jina-embeddings-v2-base-zh

Run with LlamaEdge

• LlamaEdge version: v0.14.17

• Prompt template

  • Prompt type: embedding

• Context size: 8192

• Embedding dim: 768

• Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:jina-embeddings-v2-base-zh-f16.gguf \
    llama-api-server.wasm \
    --prompt-template embedding \
    --ctx-size 8192 \
    --model-name jina-embeddings-v2-base-zh
  

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
jina-embeddings-v2-base-zh-Q2_K.gguf	Q2_K	2	82 MB	smallest, significant quality loss - not recommended for most purposes
jina-embeddings-v2-base-zh-Q3_K_L.gguf	Q3_K_L	3	100 MB	small, substantial quality loss
jina-embeddings-v2-base-zh-Q3_K_M.gguf	Q3_K_M	3	94.9 MB	very small, high quality loss
jina-embeddings-v2-base-zh-Q3_K_S.gguf	Q3_K_S	3	89.2 MB	very small, high quality loss
jina-embeddings-v2-base-zh-Q4_0.gguf	Q4_0	4	104 MB	legacy; small, very high quality loss - prefer using Q3_K_M
jina-embeddings-v2-base-zh-Q4_K_M.gguf	Q4_K_M	4	109 MB	medium, balanced quality - recommended
jina-embeddings-v2-base-zh-Q4_K_S.gguf	Q4_K_S	4	105 MB	small, greater quality loss
jina-embeddings-v2-base-zh-Q5_0.gguf	Q5_0	5	118 MB	legacy; medium, balanced quality - prefer using Q4_K_M
jina-embeddings-v2-base-zh-Q5_K_M.gguf	Q5_K_M	5	121 MB	large, very low quality loss - recommended
jina-embeddings-v2-base-zh-Q5_K_S.gguf	Q5_K_S	5	118 MB	large, low quality loss - recommended
jina-embeddings-v2-base-zh-Q6_K.gguf	Q6_K	6	133 MB	very large, extremely low quality loss
jina-embeddings-v2-base-zh-Q8_0.gguf	Q8_0	8	172 MB	very large, extremely low quality loss - not recommended
jina-embeddings-v2-base-zh-f16.gguf	f16	16	322 MB	very large, extremely low quality loss - not recommended

Quantized with llama.cpp b4273