gemma4-E4B-it-litert-128k-mtp
LiteRT-LM .litertlm bundle for Gemma 4 E4B IT, patched from the MTP-capable LiteRT community bundle to support 128k context with working speculative decoding/MTP.
Validation
Validated on 100.96.1.7 on April 12, 2026 with:
litert-lm run model.litertlm --prompt "OK" --backend cpu --enable-speculative-decoding true --verbose- successful prefill and decode
- MTP counters active (
Num drafted tokens: 12,Num verified tokens: 3)
Artifact
- SHA256:
335b70cfcc6a8772a4898a9352d65899f1925937e43a73c9e1a65f1862d1c0d4 - Source base: LiteRT community Gemma4 E4B
.litertlmbundle - Runtime contract: 128k context + MTP
- Downloads last month
- 67
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support