Gemma 4 E4B Mlx 4bit is an open-source language model by deadbydawn101. Features: 1.7b LLM, VRAM: 5.2GB, License: gemma, Quantized.
4-bit 4bit Any-to-any Apple-silicon Base model:google/gemma-4-e4b-... Base model:quantized:google/ge... Chain-of-thought Claude-code Conversational Dataset:crownelius/opus-4.6-re... En Function-calling Gemma4 Image-text-to-text Kv-cache-compression Long-context Mlx Multimodal Opus Quantized Ravenx Reasoning Region:us Safetensors Sft Tool-calling Turboquant Vision
Model Card on HF 🤗: https://huggingface.co/deadbydawn101/gemma-4-E4B-mlx-4bit
Gemma 4 E4B Mlx 4bit Parameters and Internals
| LLM Name | Gemma 4 E4B Mlx 4bit |
| Repository 🤗 | https://huggingface.co/deadbydawn101/gemma-4-E4B-mlx-4bit |
| Base Model(s) | |
| Model Size | 1.7b |
| Required VRAM | 5.2 GB |
| Updated | 2026-04-05 |
| Maintainer | deadbydawn101 |
| Model Type | gemma4 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Gemma4ForConditionalGeneration |
| License | gemma |
| Transformers Version | 5.5.0.dev0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
Rank the Gemma 4 E4B Mlx 4bit Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52554 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a