Published by google. No machine on this network has measured this family yet. The members below are what the catalog knows exists; nothing about what they can do is claimed here until somebody runs one.
what it takes, what it returns
text → vector
Declared by the network’s catalog, not measured — a signature says what this family would be asked. Whether it answered is the signed capability flags on each member.
0 of 29 builds measured · 29 still open
anchored-embeddinggemma-2-vi1 known build · not measured
EmbeddingGemma 2 BASE11 known builds · not measured
embeddinggemma-2-text-270m2 known builds · not measured
embeddinggemma-2-text-image-440m-mlx-fp321 known build · not measured
embeddinggemma-2-0.8bpw-multimodal1 known build · not measured
embeddinggemma-2-bf161 known build · not measured
embeddinggemma-2-persian-speech1 known build · not measured
embeddinggemma-2-ft-typed-decision1 known build · not measured
embeddinggemma-2-bf161 known build · not measured
embeddinggemma-21 known build · not measured
embeddinggemma-21 known build · not measured
embeddinggemma-2-ecommerce1 known build · not measured
embeddinggemma-2-Artemis-GGUF1 known build · not measured
embeddinggemma-21 known build · not measured
Sakura-EmbeddingGemma-2-AutoRound-GGUF1 known build · not measured
Sakura-EmbeddingGemma-2-HighQuality-GGUF1 known build · not measured
embeddinggemma-2-ft-typed-decision2 known builds · not measured
Builds this network knows of
Declared, not measured — this is what the catalog says exists and what it would cost a machine to hold. Nothing here is signed, and none of it claims the build works.
how much memory does your machine have
29 of 29 builds fit a 16 GB machine — budgeting 70% of it, or 11.2 GiB, because the cache and the runtime want the rest.
hf.co/ngquocvinh/EmbeddingGemma-2-GGUF:Q1_0Q1_0ollamaquantized by ngquocvinh
0.1 GiB
lethalbeats/embeddinggemma-2-0.8bpw-multimodalBF16vllmderived by lethalbeats
0.1 GiB
hf.co/ngquocvinh/EmbeddingGemma-2-GGUF:IQ1_SIQ1_Sollamaquantized by ngquocvinh
0.1 GiB
hf.co/ngquocvinh/EmbeddingGemma-2-GGUF:IQ3_XXSIQ3_XXSollamaquantized by ngquocvinh
0.1 GiB
hf.co/turintech/embeddinggemma-2-Artemis-GGUF:Q4_K_SQ4_K_Sollamaderived by turintech
0.1 GiB
hf.co/unsloth/embeddinggemma-2-GGUF:Q4_K_XLQ4_K_XLollamaquantized by unsloth
0.2 GiB
hf.co/webmp3/Sakura-EmbeddingGemma-2-HighQuality-GGUF:Q4Q4ollamaderived by webmp3
0.2 GiB
hf.co/ngquocvinh/EmbeddingGemma-2-GGUF:Q4_K_MQ4_K_Mollamaquantized by ngquocvinh
0.2 GiB
hf.co/cstr/embeddinggemma-2-ft-typed-decision-GGUF:Q8_0Q8_0ollamaderived by cstr
0.3 GiB
hf.co/unsloth/embeddinggemma-2-GGUF:Q8_0Q8_0ollamaquantized by unsloth
0.3 GiB
jayyun98/embeddinggemma-2-text-270m-mlx-bf16BF16mlxderived by jayyun98
0.5 GiB
jayyun98/embeddinggemma-2-text-270mBF16vllmderived by jayyun98
0.5 GiB
hf.co/unsloth/embeddinggemma-2-GGUF:BF16BF16ollamaquantized by unsloth
0.5 GiB
mrm8488/embeddinggemma-2-ft-typed-decisionFP32vllmderived by mrm8488
1.0 GiB
mlx-community/embeddinggemma-2-4bit4BITmlxquantized by mlx-community
1.0 GiB
hf.co/cstr/embeddinggemma-2-ft-typed-decision-GGUF:F32F32ollamaderived by cstr
1.0 GiB
mlx-community/embeddinggemma-2-5bit5BITmlxquantized by mlx-community
1.1 GiB
MohammadGholizadeh/embeddinggemma-2-persian-speechBF16vllmderived by MohammadGholizadeh
1.1 GiB
mlx-community/embeddinggemma-2-8bit8BITmlxquantized by mlx-community
1.1 GiB
webmp3/Sakura-EmbeddingGemma-2-AutoRoundINT4vllmderived by webmp3
1.2 GiB
google/embeddinggemma-2BF16vllmpublished by google
1.4 GiB
mlx-community/embeddinggemma-2-bf16BF16mlxderived by mlx-community
1.4 GiB
nativ-community/embeddinggemma-2-bf16BF16mlxderived by nativ-community
1.4 GiB
OsGo/embeddinggemma-2BF16vllmderived by OsGo
1.4 GiB
RedHatAI/embeddinggemma-2BF16vllmderived by RedHatAI
1.4 GiB
unsloth/embeddinggemma-2BF16vllmderived by unsloth
1.4 GiB
smshahbaj/embeddinggemma-2-ecommerceFP32vllmderived by smshahbaj
1.5 GiB
jayyun98/embeddinggemma-2-text-image-440m-mlx-fp32FP32mlxderived by jayyun98
1.6 GiB
ngoan/anchored-embeddinggemma-2-viBF16vllmderived by ngoan
10.1 GiB
Sizes are what the catalog declares, not what a machine measured — fitting on disk is necessary and not sufficient. Nobody here has run these on your machine, and this narrows the candidates rather than certifying one.
the same builds, by member
anchored-embeddinggemma-2-vi
ngoan/anchored-embeddinggemma-2-viBF16vllm10.1 GiB on diskderived by ngoan
EmbeddingGemma 2 BASE
hf.co/ngquocvinh/EmbeddingGemma-2-GGUF:Q1_0Q1_0ollama63 MiB on diskquantized by ngquocvinh
hf.co/ngquocvinh/EmbeddingGemma-2-GGUF:IQ1_SIQ1_Sollama95 MiB on diskquantized by ngquocvinh
hf.co/ngquocvinh/EmbeddingGemma-2-GGUF:IQ3_XXSIQ3_XXSollama129 MiB on diskquantized by ngquocvinh
hf.co/unsloth/embeddinggemma-2-GGUF:Q4_K_XLQ4_K_XLollama167 MiB on diskquantized by unsloth
hf.co/ngquocvinh/EmbeddingGemma-2-GGUF:Q4_K_MQ4_K_Mollama173 MiB on diskquantized by ngquocvinh
hf.co/unsloth/embeddinggemma-2-GGUF:Q8_0Q8_0ollama295 MiB on diskquantized by unsloth
hf.co/unsloth/embeddinggemma-2-GGUF:BF16BF16ollama532 MiB on diskquantized by unsloth
mlx-community/embeddinggemma-2-4bit4BITmlx1.0 GiB on diskquantized by mlx-community
mlx-community/embeddinggemma-2-5bit5BITmlx1.1 GiB on diskquantized by mlx-community
mlx-community/embeddinggemma-2-8bit8BITmlx1.1 GiB on diskquantized by mlx-community
google/embeddinggemma-2BF16vllm1.4 GiB on diskpublished by google
embeddinggemma-2-text-270m
jayyun98/embeddinggemma-2-text-270m-mlx-bf16BF16mlx516 MiB on diskderived by jayyun98
jayyun98/embeddinggemma-2-text-270mBF16vllm516 MiB on diskderived by jayyun98
embeddinggemma-2-text-image-440m-mlx-fp32
jayyun98/embeddinggemma-2-text-image-440m-mlx-fp32FP32mlx1.6 GiB on diskderived by jayyun98
embeddinggemma-2-0.8bpw-multimodal
lethalbeats/embeddinggemma-2-0.8bpw-multimodalBF16vllm70 MiB on diskderived by lethalbeats
embeddinggemma-2-bf16
mlx-community/embeddinggemma-2-bf16BF16mlx1.4 GiB on diskderived by mlx-community
embeddinggemma-2-persian-speech
MohammadGholizadeh/embeddinggemma-2-persian-speechBF16vllm1.1 GiB on diskderived by MohammadGholizadeh
embeddinggemma-2-ft-typed-decision
mrm8488/embeddinggemma-2-ft-typed-decisionFP32vllm1.0 GiB on diskderived by mrm8488
embeddinggemma-2-bf16
nativ-community/embeddinggemma-2-bf16BF16mlx1.4 GiB on diskderived by nativ-community
embeddinggemma-2
OsGo/embeddinggemma-2BF16vllm1.4 GiB on diskderived by OsGo
embeddinggemma-2
RedHatAI/embeddinggemma-2BF16vllm1.4 GiB on diskderived by RedHatAI
embeddinggemma-2-ecommerce
smshahbaj/embeddinggemma-2-ecommerceFP32vllm1.5 GiB on diskderived by smshahbaj
embeddinggemma-2-Artemis-GGUF
hf.co/turintech/embeddinggemma-2-Artemis-GGUF:Q4_K_SQ4_K_Sollama149 MiB on diskderived by turintech
embeddinggemma-2
unsloth/embeddinggemma-2BF16vllm1.4 GiB on diskderived by unsloth
Sakura-EmbeddingGemma-2-AutoRound-GGUF
webmp3/Sakura-EmbeddingGemma-2-AutoRoundINT4vllm1.2 GiB on diskderived by webmp3
Sakura-EmbeddingGemma-2-HighQuality-GGUF
hf.co/webmp3/Sakura-EmbeddingGemma-2-HighQuality-GGUF:Q4Q4ollama168 MiB on diskderived by webmp3
embeddinggemma-2-ft-typed-decision
hf.co/cstr/embeddinggemma-2-ft-typed-decision-GGUF:Q8_0Q8_0ollama293 MiB on diskderived by cstr
hf.co/cstr/embeddinggemma-2-ft-typed-decision-GGUF:F32F32ollama1.0 GiB on diskderived by cstr
ask your own gram
Your concierge can answer this from the network rather than from this page. The ask carries the operator id, so it resolves to a capability and an engine — not to a name somebody has to recognise.
What has this network measured about the EmbeddingGemma 2 family (epn.family.embeddinggemma-2), and can my gram run any of it? See /inferences/embeddinggemma-2