LogiShell store Open app

Store › model › Embeddings

EmbeddingGemma-2-GGUF

by ngquocvinh · source Hugging Face · updated 2026-10-08

apache-2.0173 MB~1 GB RAMsource aliveunlabeled

Community GGUF quantizations of google/embeddinggemma-2.

Add to LogiShell Open in the web IDE

The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:ngquocvinh/EmbeddingGemma-2-GGUF and its progress lives in the Resource Center.

Source and license

Numbers

Numbers as of 2026-10-09 19:01 UTC, from the source API.

Summary

Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.

Reviews

No reviews yet. Reviews are written inside LogiShell: open this card in the app.

Files

filequantsize
EmbeddingGemma-2-IQ1_M.ggufIQ1_M98 MB
EmbeddingGemma-2-IQ1_S.ggufIQ1_S96 MB
EmbeddingGemma-2-IQ2_M.ggufIQ2_M125 MB
EmbeddingGemma-2-IQ2_S.ggufIQ2_S122 MB
EmbeddingGemma-2-IQ2_XS.ggufIQ2_XS106 MB
EmbeddingGemma-2-IQ2_XXS.ggufIQ2_XXS102 MB
EmbeddingGemma-2-IQ3_M.ggufIQ3_M139 MB
EmbeddingGemma-2-IQ3_S.ggufIQ3_S136 MB
EmbeddingGemma-2-IQ3_XS.ggufIQ3_XS133 MB
EmbeddingGemma-2-IQ3_XXS.ggufIQ3_XXS129 MB
EmbeddingGemma-2-IQ4_NL.ggufIQ4_NL169 MB
EmbeddingGemma-2-IQ4_XS.ggufIQ4_XS162 MB
EmbeddingGemma-2-Q1_0.ggufQ1_063 MB
EmbeddingGemma-2-Q2_K.ggufQ2_K115 MB
EmbeddingGemma-2-Q2_K_S.ggufQ2_K_S111 MB
EmbeddingGemma-2-Q3_K_L.ggufQ3_K_L147 MB
EmbeddingGemma-2-Q3_K_M.ggufQ3_K_M142 MB
EmbeddingGemma-2-Q3_K_S.ggufQ3_K_S136 MB
EmbeddingGemma-2-Q4_K_M.ggufQ4_K_M173 MB
EmbeddingGemma-2-Q4_K_S.ggufQ4_K_S170 MB
EmbeddingGemma-2-Q5_K_M.ggufQ5_K_M203 MB
EmbeddingGemma-2-Q5_K_S.ggufQ5_K_S201 MB
EmbeddingGemma-2-Q6_K.ggufQ6_K234 MB
EmbeddingGemma-2-Q8_0.ggufQ8_0296 MB
EmbeddingGemma-2-TQ1_0.ggufTQ1_0126 MB
EmbeddingGemma-2-TQ2_0.ggufTQ2_0132 MB
mmproj-EmbeddingGemma-2-BF16.ggufBF16937 MB

From the source README

EmbeddingGemma 2 GGUF

Community GGUF quantizations of google/embeddinggemma-2.

☕ If this GGUF made your day easier, a coffee would make mine.
Send a coffee ☕
I build and test these releases myself. Your coffee helps keep me going.
Thank you for supporting this work.

About EmbeddingGemma 2

EmbeddingGemma 2 is a multilingual, multimodal embedding model from Google DeepMind. It maps text and code, images, video, and audio into a shared 768-dimensional vector space and has an 8,192-token shared context window. The upstream checkpoint has a 270M-parameter text path plus optional vision and audio encoders. This release contains a quantized text backbone and a shared BF16 vision/audio projector. Text, image, and audio inputs returned normalized 768-dimensional vectors in local `llama-server` CPU smoke checks. See the official model card for supported task prefixes, modalities, and input guidance.

Embedding evaluation

Every value below comes from local measurements of the locked BF16 GGUF and quantized files; the numbers are not copied from the upstream model card. The fixed task evaluation uses the 1,379-pair test split of MTEB STSBenchmark STS, dataset revision `96943a16ea6a35129e253c659081cb59daf81b30`. It covers 2,552 unique sentences with the `task: sentence similarity | query:` prefix, an 8,192-token context, and the CPU `llama.cpp` runtime at commit `9c2e0e491a822adae1f0b1c831adb4160057d24f`. Spearman and Pearson measure correlation between cosine similarity and human scores. Mean and 5th-percentile cosine measure vector agreement with the BF16 GGUF reference. Higher values indicate stronger task correlation or closer vector agreement; smaller files use less disk. This is a task-specif…

Source: https://huggingface.co/ngquocvinh/EmbeddingGemma-2-GGUF

Card id model:hf:ngquocvinh/EmbeddingGemma-2-GGUF · collected 2026-10-09 19:01 UTC · JSON