gemma-4-E4B-it-qat-mobile-ct
Support summary
gemma-4-E4B-it-qat-mobile-ct is a checkpoint published by Google, built on the Gemma4ForConditionalGeneration architecture. Official recipes or cookbooks cover vLLM, without pinning a stable release.
- Documented quantization
- int2/4/8
- Configured context
- 131,072 tokens
- License
- apache-2.0
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Hugging Face model card
- Publisher
- Task
- any to any
- License
- apache-2.0
- Library
- transformers
- Architecture
- Gemma4ForConditionalGeneration
- Weight tensor elements
- 8.7B
- Tensor types
- I64, F32, I32, BF16, I8
- Quantization
- compressed-tensors · pack-quantized
- Configured context
- 131,072 tokens
- Base models
- google/gemma-4-E4B-it-qat-mobile-transformers
- Weight access
- Public
- Repository created
- 2026-06-01
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | Version not pinnedRecipe / cookbook | Documented recipeSource: vllm · models/Google/gemma-4-E4B-it.yamlReviewed | No supported release indexed | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||