No machine on this network has measured this model yet. Everything below is what the catalog knows exists — where the weights come from, how large each build is, and whose work it is. Nothing here is a claim about what the model can do; that only appears once a machine has run it and signed the result.
hf.co/ngquocvinh/EmbeddingGemma-2-GGUF:Q1_0ollama · Q1_0 · 0.1 GiB · quantizer (ngquocvinh)
hf.co/ngquocvinh/EmbeddingGemma-2-GGUF:IQ1_Sollama · IQ1_S · 0.1 GiB · quantizer (ngquocvinh)
hf.co/ngquocvinh/EmbeddingGemma-2-GGUF:IQ3_XXSollama · IQ3_XXS · 0.1 GiB · quantizer (ngquocvinh)
hf.co/unsloth/embeddinggemma-2-GGUF:Q4_K_XLollama · Q4_K_XL · 0.2 GiB · quantizer (unsloth)
hf.co/ngquocvinh/EmbeddingGemma-2-GGUF:Q4_K_Mollama · Q4_K_M · 0.2 GiB · quantizer (ngquocvinh)
hf.co/unsloth/embeddinggemma-2-GGUF:Q8_0ollama · Q8_0 · 0.3 GiB · quantizer (unsloth)
hf.co/unsloth/embeddinggemma-2-GGUF:BF16ollama · BF16 · 0.5 GiB · quantizer (unsloth)
mlx-community/embeddinggemma-2-4bitmlx · 4BIT · 1.0 GiB · quantizer (mlx-community)
mlx-community/embeddinggemma-2-5bitmlx · 5BIT · 1.1 GiB · quantizer (mlx-community)
mlx-community/embeddinggemma-2-8bitmlx · 8BIT · 1.1 GiB · quantizer (mlx-community)
google/embeddinggemma-2vllm · BF16 · 1.4 GiB · vendor (google)