evie-compact-tier — Evie mirror

The on-device models for Evie's compact tier (iPhone and iPad with 4 GB of memory), re-hosted for availability and immutable pinning. Files are unmodified.

File	Source	sha256
`gemma-4-E2B-it.litertlm`	`litert-community/gemma-4-E2B-it-litert-lm` @ `b3ca0d2f076785a8f4b2219ddbd2bdb99954eae1`	`181938105e0eefd105961417e8da75903eacda102c4fce9ce90f50b97139a63c`
`kokoro/model.onnx`	`csukuangfj/kokoro-multi-lang-v1_0` @ `f7b96bb6bef5c5da4d3aa4f4e0498fbbf62dc78b` (k2-fsa export of Kokoro v1.0, fp32)	`b40f62b166ac8164b0627ef48a0b358eda0985e272fb03ef5252e7206305da11`

Gemma 4 is released by Google under the Apache License 2.0; "Gemma" is a trademark of Google LLC. Kokoro-82M is by hexgrad, Apache License 2.0. Not affiliated with or endorsed by Google, hexgrad or k2-fsa.

Downloads last month: 279

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Milewuigrhi3/evie-compact-tier

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Quantized

(418)

this model