4 builds of embeddinggemma-300m-gguf measured on real machines — different packagers, precisions and engines, each a different file with its own numbers. The best each engine proved is first; every build has its own page with the machines and signatures behind it.
no context proved on this engine yet
proved by at least one build: Embeddings
| build | publisher | precision | engine | whose work | context proved | best tok/s | machines |
|---|---|---|---|---|---|---|---|
| hf.co/lm-kit/embeddinggemma-300m-gguf:F16 | lm-kit | F16 | ollama | derivative | — | — | 1 |
| hf.co/lm-kit/embeddinggemma-300m-gguf:Q4_K_M | lm-kit | Q4_K_M | ollama | derivative | — | — | 1 |
| hf.co/lm-kit/embeddinggemma-300m-gguf:Q5_K_M | lm-kit | Q5_K_M | ollama | derivative | — | — | 1 |
| hf.co/lm-kit/embeddinggemma-300m-gguf:Q8_0 | lm-kit | Q8_0 | ollama | derivative | — | — | 1 |