Instructions to use metricspace/gemma4-E4B-it-litert-128k-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use metricspace/gemma4-E4B-it-litert-128k-mtp with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli # A single .litertlm file in the repo is picked automatically; otherwise the CLI asks which one to run # (or pass its name right after the repo id). litert-lm run \ --from-huggingface-repo=metricspace/gemma4-E4B-it-litert-128k-mtp \ --prompt="Write me a poem"
- Notebooks
- Google Colab
- Kaggle
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
- 46
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support