LLM EXPLORER 57,918 MODELS INDEXED

Gemma 3n E4B Unsloth Bnb 4bit by unsloth

By unsloth · 189 downloads

Gemma 3n E4B Unsloth Bnb 4bit is an open-source language model by unsloth. Features: 7.8b LLM, VRAM: 9.8GB, License: gemma, Quantized, LLM Explorer Score: 0.32, ELO: 1318.

  Arxiv:1705.03551   Arxiv:1903.00161   Arxiv:1904.09728   Arxiv:1905.07830   Arxiv:1905.10044   Arxiv:1907.10641   Arxiv:1911.01547   Arxiv:1911.11641   Arxiv:2009.03300   Arxiv:2107.03374   Arxiv:2108.07732   Arxiv:2210.03057   Arxiv:2311.12022   Arxiv:2403.07974   Arxiv:2411.19799   Arxiv:2502.12404   Arxiv:2502.21228   4-bit   4bit Base model:google/gemma-3n-e4b... Base model:quantized:google/ge...   Bitsandbytes   En   Endpoints compatible   Gemma   Gemma3   Gemma3n   Google   Image-text-to-text   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Unsloth

Gemma 3n E4B Unsloth Bnb 4bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Gemma 3n E4B Unsloth Bnb 4bit Parameters and Internals

LLM NameGemma 3n E4B Unsloth Bnb 4bit
Repository πŸ€—https://huggingface.co/unsloth/gemma-3n-E4B-unsloth-bnb-4bit 
Base Model(s)  Gemma 3n E4B It   google/gemma-3n-E4B-it
Model Size7.8b
Required VRAM9.8 GB
Updated2026-08-10
Maintainerunsloth
Model Typegemma3n
Model Files  3.7 GB: 1-of-3   5.0 GB: 2-of-3   1.1 GB: 3-of-3
Supported Languagesen
Quantization Type4bit
Model ArchitectureGemma3nForConditionalGeneration
Licensegemma
Model Max Length32768
Transformers Version4.53.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Torch Data Typebfloat16

Best Alternatives to Gemma 3n E4B Unsloth Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...mma 3n E4B It Unsloth Bnb 4bit0K / 9.8 GB16499
Gemma 3n E4B It0K / 15.8 GB35121919
MedraN E4B0K / 15.8 GB50
Note: green Score (e.g. "73.2") means that the model is better than unsloth/gemma-3n-E4B-unsloth-bnb-4bit.