What are the hardware requirements for Vi Gemma 2B RAG?

Vi Gemma 2B RAG requires approximately 5.1 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Vi Gemma 2B RAG and how large is it?

Vi Gemma 2B RAG is developed by ricepaper, a model with 2b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Vi Gemma 2B RAG?

Vi Gemma 2B RAG is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Vi Gemma 2B RAG by ricepaper — VRAM 5.1GB, 8K context

Name: Vi Gemma 2B RAG
Author: ricepaper

Vi Gemma 2B RAG is an open-source language model by ricepaper. Features: 2b LLM, VRAM: 5.1GB, Context: 8K, License: apache-2.0, Quantized, LLM Explorer Score: 0.13.

4bit Base model:finetune:unsloth/ge... Base model:unsloth/gemma-1.1-2... Conversational En Endpoints compatible Gemma Pytorch Quantized Region:us Retrieval-augmented-generation Safetensors Sft Sharded Tensorflow Trl Unsloth Vi

Model Card on HF 🤗: https://huggingface.co/ricepaper/vi-gemma-2b-RAG

Vi Gemma 2B RAG Parameters and Internals

LLM Name	Vi Gemma 2B RAG
Repository 🤗	https://huggingface.co/ricepaper/vi-gemma-2b-RAG
Base Model(s)	unsloth/gemma-1.1-2b-it-bnb-4bit unsloth/gemma-1.1-2b-it-bnb-4bit
Model Size	2b
Required VRAM	5.1 GB
Updated	2026-08-06
Maintainer	ricepaper
Model Type	gemma
Model Files	5.0 GB: 1-of-2 0.1 GB: 2-of-2 5.0 GB: 1-of-2 0.1 GB: 2-of-2
Supported Languages	en vi
Quantization Type	4bit
Model Architecture	GemmaForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.43.3
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	256000
Torch Data Type	float16

Rank the Vi Gemma 2B RAG capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Vi Gemma 2B RAG

Best Alternatives	Context / RAM	Downloads	Likes
... 2B It Hermes Function Calling	8K / 5.1 GB	18	0
My AwesomeFinance Model	8K / 2.1 GB	7	0
... 2.8 Gemma 2B HQQ 1bit Smashed	8K / 1.3 GB	5	0
... 2.8 Gemma 2B HQQ 2bit Smashed	8K / 1.6 GB	5	0
... 2.8 Gemma 2B HQQ 4bit Smashed	8K / 2.1 GB	5	0
Emo AI 3B	8K / 5.1 GB	6	1
Jenna V3 QGemma 2B	8K / 5.1 GB	6	0
Gemma 2B Sentiment	8K / 5.1 GB	13	0
Jenna V2	8K / 5.1 GB	6	0
... 2.8 Gemma 2B Bnb 4bit Smashed	8K / 2.2 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than ricepaper/vi-gemma-2b-RAG.