Gemma 4 E2B It Qat 4bit is an open-source language model by mlx-community. Features: 1.4b LLM, VRAM: 4.3GB, Quantized, LLM Explorer Score: 0.28.
| LLM Name | Gemma 4 E2B It Qat 4bit |
| Repository π€ | https://huggingface.co/mlx-community/gemma-4-E2B-it-qat-4bit |
| Model Size | 1.4b |
| Required VRAM | 4.3 GB |
| Updated | 2026-08-08 |
| Maintainer | mlx-community |
| Model Type | gemma4 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Gemma4ForConditionalGeneration |
| Transformers Version | 5.6.2 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Gemma 4 E2B It UD MLX 4bit | 0K / 4.5 GB | 1117 | 23 |