Downloads · 30 days
0
DarrenJiaImbue/gemma-4-E4B-it-qat-litertlm
gemma-4-E4B-it-qat-litertlm is a text generation model from DarrenJiaImbue. Use it when you need the model to write or continue text. It is set up for litert. The card lists the license as apache-2.0.
Unofficial conversion of google/gemma-4-E4B-it-qat-mobile-transformers to LiteRT-LM .litertlm format, produced entirely from the public QAT mobile checkpoint with a patched litert-torch
Downloads · 30 days
0
Access
Public
Updated Jul 7, 2026
Repo size
3.3 GB
Likes
1
Public
Click a slice to open those files.
.litertlm3.3 GB · 100%
From the Hugging Face model README
Unofficial conversion of
google/gemma-4-E4B-it-qat-mobile-transformers
to LiteRT-LM .litertlm format, produced entirely from the public QAT mobile
checkpoint with a patched
litert-torch
(adds the quantized-safetensors import path requested in
google-ai-edge/litert-torch#998
and #1044).
No weights were taken from the official prebuilt litert-community/gemma-4-E4B-it-litert-lm; it was used only for verification. The chat template is the LiteRT-compatible template from that repo (the checkpoint's own template uses Jinja constructs the runtime's minijinja engine cannot render).
The QAT quantization is preserved bit-exactly (verified tensor-by-tensor against the official bundle):
per_layer_model_projection, is stored unquantized in the
public checkpoint)| model | CPU backend | GPU backend |
|---|---|---|
| official prebuilt | 35/35 | — |
| this bundle | 34/35 | 34/35 |
30/35 outputs are token-identical to the official prebuilt on CPU.
Text-only (no vision/audio/drafter sections). prefill_128/prefill_1024
signatures, cache length 4096, f32 KV cache, dynamic-range int2/int4/int8
weights (gemma4_qat_w248 recipe), ~3.25 GB.
# pip install litert-lm
import litert_lm
engine = litert_lm.Engine("model.litertlm", backend=litert_lm.Backend.CPU())
conv = engine.create_conversation(
sampler_config=litert_lm.SamplerConfig(top_k=1))
print(conv.send_message("What is the capital of France?"))
Gemma is provided under and subject to the terms of the upstream model's license; see the base model card.