What are the hardware requirements for MedGPT Gemma2 9B BA V.1?

MedGPT Gemma2 9B BA V.1 requires approximately 18.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MedGPT Gemma2 9B BA V.1 and how large is it?

MedGPT Gemma2 9B BA V.1 is developed by valeriojob, a model with 9b 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 MedGPT Gemma2 9B BA V.1?

MedGPT Gemma2 9B BA V.1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MedGPT Gemma2 9B BA V.1 by valeriojob — VRAM 18.6GB

Name: MedGPT Gemma2 9B BA V.1
Author: valeriojob

MedGPT Gemma2 9B BA V.1 is an open-source language model by valeriojob. Features: 9b LLM, VRAM: 18.6GB, License: apache-2.0, LLM Explorer Score: 0.13.

Base model:finetune:unsloth/ge... Base model:unsloth/gemma-2-9b En Endpoints compatible Gemma2 Llama Lora Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/valeriojob/MedGPT-Gemma2-9B-BA-v.1

MedGPT Gemma2 9B BA V.1 Parameters and Internals

Model Type

text-generation-inference, transformers

Use Cases

Areas:

Medical assistance, Administrative tasks

Applications:

Research, Prototyping

Primary Use Cases:

Supplementary assistance for General Practitioners (GPs)

Limitations:

Not suitable for production use

Considerations:

Model created as an initial prototype in the context of a bachelor thesis.

Supported Languages

en (English)

Training Details

Data Sources:

datasets/valeriojob/BA-v.1

Data Volume:

60 examples

Methodology:

Fine-tuning using Unsloth and Huggingface's TRL library

Model Architecture:

Fine-tuned model from Gemma-2-9B

LLM Name	MedGPT Gemma2 9B BA V.1
Repository 🤗	https://huggingface.co/valeriojob/MedGPT-Gemma2-9B-BA-v.1
Base Model(s)	Gemma 2 9B unsloth/gemma-2-9b
Model Size	9b
Required VRAM	18.6 GB
Updated	2026-07-10
Maintainer	valeriojob
Model Files	0.4 GB 4.9 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 3.7 GB: 4-of-4
Supported Languages	en
Model Architecture	AutoModelForCausalLM
License	apache-2.0
Model Max Length	8192
Is Biased	none
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	gate_proj\|v_proj\|o_proj\|q_proj\|up_proj\|down_proj\|k_proj
LoRA Alpha	16
LoRA Dropout	0
R Param	32

Rank the MedGPT Gemma2 9B BA V.1 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 MedGPT Gemma2 9B BA V.1

Best Alternatives	Context / RAM	Downloads
ZYR3.1MoE	0K / 17.9 GB	259
Gemma 2 KoMed Lr2e 5	0K / 18.6 GB	22
Gemma 2 9B Nopcsa Finetune	0K / 18.6 GB	15

Note: green Score (e.g. "73.2") means that the model is better than valeriojob/MedGPT-Gemma2-9B-BA-v.1.