LLM EXPLORER 56,604 MODELS INDEXED

Gemma 2B Bnb 4bit by unsloth

By unsloth · 2082 downloads
HF Repo ↗ Copy URL

Gemma 2B Bnb 4bit is an open-source language model by unsloth. Features: 2b LLM, VRAM: 2.1GB, Context: 8K, License: apache-2.0, Quantized, LLM Explorer Score: 0.13.

  4-bit   4bit   Bitsandbytes   Bnb   En   Endpoints compatible   Gemma   Gemma-2b   Quantized   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/gemma-2b-bnb-4bit 

Gemma 2B Bnb 4bit Parameters and Internals

Model Type 
transformers
Additional Notes 
Fine-tuning models can be done using Google Colab notebooks for free.
Input Output 
Accepted Modalities:
text
LLM NameGemma 2B Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/gemma-2b-bnb-4bit 
Model Size2b
Required VRAM2.1 GB
Updated2026-08-08
Maintainerunsloth
Model Typegemma
Model Files  2.1 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureGemmaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.44.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Quantized Models of the Gemma 2B Bnb 4bit

Model
Likes
Downloads
VRAM
... 2B It Hermes Function Calling0185 GB
Gemma Help Tiny Sft1215 GB
Emo AI 3B165 GB
Jenna Gemma V01 Gguf 8bit1412 GB
Jenna Gemma V01 Gguf Q40321 GB
Jenna Gemma V01 Gguf 16bit0235 GB
Test Model072 GB
PRIME DeCyphers Final115 GB
Mode Gemma0292 GB
Gemma 2B Malayalam Gguf1621 GB

Best Alternatives to Gemma 2B Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
... 2B It Hermes Function Calling8K / 5.1 GB180
Vi Gemma 2B RAG8K / 5.1 GB3613
My AwesomeFinance Model8K / 2.1 GB70
... 2.8 Gemma 2B HQQ 1bit Smashed8K / 1.3 GB50
... 2.8 Gemma 2B HQQ 2bit Smashed8K / 1.6 GB50
... 2.8 Gemma 2B HQQ 4bit Smashed8K / 2.1 GB50
Emo AI 3B8K / 5.1 GB61
Jenna V3 QGemma 2B8K / 5.1 GB60
Gemma 2B Sentiment8K / 5.1 GB130
Jenna V28K / 5.1 GB60
Note: green Score (e.g. "73.2") means that the model is better than unsloth/gemma-2b-bnb-4bit.