Downloads · 30 days
0
gemma-4-E2B-it-qat-heretic-LiteRT
Calandracas/gemma-4-E2B-it-qat-heretic-LiteRT
gemma-4-E2B-it-qat-heretic-LiteRT is a any-to-any model from Calandracas. Use it for the any-to-any task on the model card, and read the license before you ship it in a product. It is set up for litertlm. The card lists the license as apache-2.0.
- Format: LiteRT-LM .litertlm (weights + tokenizer + graph in one file) - Runtime: LiteRT-LM (XNNPACK CPU / OpenCL GPU) - Source checkpoint: coder3101/gemma-4-E2B-it-qat-q40-unquantized-heretic - Base model(s):
Access
Public
Updated Jul 5, 2026
Repo size
2.6 GB
Likes
3
Trending 1
Repo makeup
Click a slice to open those files.
.litertlm2.6 GB · 100%
At a glance
- Task
- Any-to-Any
- Library
- litertlm
- License
- apache-2.0
- Access
- Public
- Created
- Jul 5, 2026
- Updated
- Jul 5, 2026
- SHA
- a2a0ae45
Base models
Model card
From the Hugging Face model README
gemma-4-E2B-it-qat-heretic-LiteRT
Model details
-
Format: LiteRT-LM
.litertlm(weights + tokenizer + graph in one file) -
Runtime: LiteRT-LM (XNNPACK CPU / OpenCL GPU)
-
Source checkpoint:
coder3101/gemma-4-E2B-it-qat-q4_0-unquantized-heretic -
Base model(s):
-
coder3101/gemma-4-E2B-it-qat-q4_0-unquantized-heretic -
Quantization:
mixed48(Google gemma4 mixed 4/8-bit mobile scheme (INT4 weights + INT8 projections)) -
License:
apache-2.0 AND agpl-3.0
How it was produced
Converted with convert_gemma4.py, which runs the same three stages described in the Google ai-edge-quantizer docs:
- Export — HF checkpoint (PyTorch/safetensors) → float TFLite flatbuffer (via
litert-torchexport_hf) - Quantize — float TFLite → quantized TFLite (via
ai-edge-quantizerrecipemixed48) - Package — quantized TFLite →
.litertlmbundle (vialitert-torchlitert_lm_builder)
No weights were modified, retrained, or merged — only reformatted and quantized.
Usage
Load model.litertlm with any LiteRT-LM runtime or client. Place it under your
app's models folder and the runtime loads it automatically.
- Task
- Any-to-Any
- Library
- litertlm
- License
- apache-2.0
- Created
- Jul 5, 2026
- Updated
- Jul 5, 2026