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
EmbeddingGemma 300M9 known builds · not measured
EmbeddingGemma-300M-MLX-8bit1 known build · not measured
EmbeddingGemma-300M-LawVault1 known build · not measured
embeddinggemma-300m-GGUF-with-dense-modules3 known builds · not measured
embeddinggemma-300m1 known build · not measured
embeddinggemma-300m-qat-q8_0-unquantized1 known build · not measured
embeddinggemma-300m-8bit-hi-mlx1 known build · not measured
embeddinggemma-300m-gguf4 known builds · not measured
embeddinggemma-300m1 known build · not measured
embeddinggemma-300m-4bit1 known build · not measured
embeddinggemma-300m-qat-q8_0-unquantized-bf161 known build · not measured
embeddinggemma-300m1 known build · not measured
embeddinggemma-300m-code-8L-distill-int81 known build · not measured
embeddinggemma-300m-medical1 known build · not measured
embeddinggemma-300m-6bit1 known build · not measured
embeddinggemma-300m-qat-q8_0-unquantized1 known build · 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.
mlx-community/embeddinggemma-300m-4bitFP32mlxderived by mlx-community
0.2 GiB
hf.co/gaianet/embeddinggemma-300m-GGUF:Q2_KQ2_Kollamaquantized by gaianet
0.2 GiB
hf.co/gaianet/embeddinggemma-300m-GGUF:Q3_K_SQ3_K_Sollamaquantized by gaianet
0.2 GiB
hf.co/gaianet/embeddinggemma-300m-GGUF:Q4_K_MQ4_K_Mollamaquantized by gaianet
0.2 GiB
hf.co/lm-kit/embeddinggemma-300m-gguf:Q4_K_MQ4_K_Mollamaderived by lm-kit
0.2 GiB
hf.co/cduk/embeddinggemma-300m-GGUF-with-dense-modules:Q4_KQ4_Kollamaderived by cduk
0.2 GiB
hf.co/lm-kit/embeddinggemma-300m-gguf:Q5_K_MQ5_K_Mollamaderived by lm-kit
0.2 GiB
sjoerdbodbijl/embeddinggemma-300m-6bitFP32mlxderived by sjoerdbodbijl
0.2 GiB
hf.co/cduk/embeddinggemma-300m-GGUF-with-dense-modules:Q6_KQ6_Kollamaderived by cduk
0.2 GiB
sensiarion/embeddinggemma-300m-code-8L-distill-int8FP32mlxderived by sensiarion
0.2 GiB
hf.co/unsloth/embeddinggemma-300m-GGUF:Q4_0Q4_0ollamaquantized by unsloth
0.3 GiB
janihal/embeddinggemma-300m-8bit-mlxFP32mlxquantized by janihal
0.3 GiB
aufklarer/EmbeddingGemma-300M-MLX-8bitBF16mlxderived by aufklarer
0.3 GiB
hf.co/lm-kit/embeddinggemma-300m-gguf:Q8_0Q8_0ollamaderived by lm-kit
0.3 GiB
hf.co/ggml-org/embeddinggemma-300M-GGUF:Q8_0Q8_0ollamaquantized by ggml-org
0.3 GiB
hf.co/cduk/embeddinggemma-300m-GGUF-with-dense-modules:Q8_0Q8_0ollamaderived by cduk
0.3 GiB
janihal/embeddinggemma-300m-8bit-hi-mlxFP32mlxderived by janihal
0.5 GiB
hf.co/unsloth/embeddinggemma-300m-GGUF:BF16BF16ollamaquantized by unsloth
0.6 GiB
hf.co/lm-kit/embeddinggemma-300m-gguf:F16F16ollamaderived by lm-kit
0.6 GiB
mlx-community/embeddinggemma-300m-qat-q8_0-unquantized-bf16FP32mlxderived by mlx-community
0.6 GiB
hf.co/unsloth/embeddinggemma-300m-GGUF:F32F32ollamaquantized by unsloth
1.1 GiB
unsloth/embeddinggemma-300mFP32vllmquantized by unsloth
1.1 GiB
ByronLeeee/EmbeddingGemma-300M-LawVaultFP32vllmderived by ByronLeeee
1.1 GiB
h2oai/embeddinggemma-300mFP32vllmderived by h2oai
1.1 GiB
h2oai/embeddinggemma-300m-qat-q8_0-unquantizedFP32vllmderived by h2oai
1.1 GiB
michaelfeil/embeddinggemma-300mFP32vllmderived by michaelfeil
1.1 GiB
RedHatAI/embeddinggemma-300mFP32vllmderived by RedHatAI
1.1 GiB
sentence-transformers/embeddinggemma-300m-medicalFP32vllmderived by sentence-transformers
1.1 GiB
unsloth/embeddinggemma-300m-qat-q8_0-unquantizedFP32vllmderived by unsloth
1.1 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
EmbeddingGemma 300M
hf.co/gaianet/embeddinggemma-300m-GGUF:Q2_KQ2_Kollama202 MiB on diskquantized by gaianet
hf.co/gaianet/embeddinggemma-300m-GGUF:Q3_K_SQ3_K_Sollama208 MiB on diskquantized by gaianet
hf.co/gaianet/embeddinggemma-300m-GGUF:Q4_K_MQ4_K_Mollama225 MiB on diskquantized by gaianet
hf.co/unsloth/embeddinggemma-300m-GGUF:Q4_0Q4_0ollama264 MiB on diskquantized by unsloth
janihal/embeddinggemma-300m-8bit-mlxFP32mlx311 MiB on diskquantized by janihal
hf.co/ggml-org/embeddinggemma-300M-GGUF:Q8_0Q8_0ollama318 MiB on diskquantized by ggml-org
hf.co/unsloth/embeddinggemma-300m-GGUF:BF16BF16ollama584 MiB on diskquantized by unsloth
hf.co/unsloth/embeddinggemma-300m-GGUF:F32F32ollama1.1 GiB on diskquantized by unsloth
unsloth/embeddinggemma-300mFP32vllm1.1 GiB on diskquantized by unsloth
EmbeddingGemma-300M-MLX-8bit
aufklarer/EmbeddingGemma-300M-MLX-8bitBF16mlx311 MiB on diskderived by aufklarer
EmbeddingGemma-300M-LawVault
ByronLeeee/EmbeddingGemma-300M-LawVaultFP32vllm1.1 GiB on diskderived by ByronLeeee
embeddinggemma-300m-GGUF-with-dense-modules
hf.co/cduk/embeddinggemma-300m-GGUF-with-dense-modules:Q4_KQ4_Kollama227 MiB on diskderived by cduk
hf.co/cduk/embeddinggemma-300m-GGUF-with-dense-modules:Q6_KQ6_Kollama252 MiB on diskderived by cduk
hf.co/cduk/embeddinggemma-300m-GGUF-with-dense-modules:Q8_0Q8_0ollama318 MiB on diskderived by cduk
embeddinggemma-300m
h2oai/embeddinggemma-300mFP32vllm1.1 GiB on diskderived by h2oai
embeddinggemma-300m-qat-q8_0-unquantized
h2oai/embeddinggemma-300m-qat-q8_0-unquantizedFP32vllm1.1 GiB on diskderived by h2oai
embeddinggemma-300m-8bit-hi-mlx
janihal/embeddinggemma-300m-8bit-hi-mlxFP32mlx502 MiB on diskderived by janihal
embeddinggemma-300m-gguf
hf.co/lm-kit/embeddinggemma-300m-gguf:Q4_K_MQ4_K_Mollama225 MiB on diskderived by lm-kit
hf.co/lm-kit/embeddinggemma-300m-gguf:Q5_K_MQ5_K_Mollama235 MiB on diskderived by lm-kit
hf.co/lm-kit/embeddinggemma-300m-gguf:Q8_0Q8_0ollama313 MiB on diskderived by lm-kit
hf.co/lm-kit/embeddinggemma-300m-gguf:F16F16ollama584 MiB on diskderived by lm-kit
embeddinggemma-300m
michaelfeil/embeddinggemma-300mFP32vllm1.1 GiB on diskderived by michaelfeil
embeddinggemma-300m-4bit
mlx-community/embeddinggemma-300m-4bitFP32mlx165 MiB on diskderived by mlx-community
embeddinggemma-300m-qat-q8_0-unquantized-bf16
mlx-community/embeddinggemma-300m-qat-q8_0-unquantized-bf16FP32mlx586 MiB on diskderived by mlx-community
embeddinggemma-300m
RedHatAI/embeddinggemma-300mFP32vllm1.1 GiB on diskderived by RedHatAI
embeddinggemma-300m-code-8L-distill-int8
sensiarion/embeddinggemma-300m-code-8L-distill-int8FP32mlx252 MiB on diskderived by sensiarion
embeddinggemma-300m-medical
sentence-transformers/embeddinggemma-300m-medicalFP32vllm1.1 GiB on diskderived by sentence-transformers
embeddinggemma-300m-6bit
sjoerdbodbijl/embeddinggemma-300m-6bitFP32mlx238 MiB on diskderived by sjoerdbodbijl
embeddinggemma-300m-qat-q8_0-unquantized
unsloth/embeddinggemma-300m-qat-q8_0-unquantizedFP32vllm1.1 GiB on diskderived by unsloth
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 family (epn.family.embeddinggemma), and can my gram run any of it? See /inferences/embeddinggemma