What are the hardware requirements for Onca 3.0 12B?

Onca 3.0 12B requires approximately 24.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Onca 3.0 12B and how large is it?

Onca 3.0 12B is developed by Joesh1, a model with 12b 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 Onca 3.0 12B?

Onca 3.0 12B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Onca 3.0 12B by Joesh1 — VRAM 24.1GB

Name: Onca 3.0 12B
Author: Joesh1

Onca 3.0 12B is an open-source language model by Joesh1. Features: 12b LLM, VRAM: 24.1GB, License: cc-by-nc-4.0, LLM Explorer Score: 0.28.

Base model:finetune:google/gem... Base model:google/gemma-4-12b Clinical-trials En Endpoints compatible Gemma4 unified Grpo Image-text-to-text Onca-3.0-12b Oncology Pathology Precision-oncology Region:us Research Safetensors Sharded Structured-generation Tensorflow

Model Card on HF 🤗: https://huggingface.co/Joesh1/onca-3.0-12b

Onca 3.0 12B Parameters and Internals

LLM Name	Onca 3.0 12B
Repository 🤗	https://huggingface.co/Joesh1/onca-3.0-12b
Base Model(s)	Gemma 4 12B google/gemma-4-12B
Model Size	12b
Required VRAM	24.1 GB
Updated	2026-09-11
Maintainer	Joesh1
Model Type	gemma4_unified
Model Files	2.4 GB: 1-of-11 2.4 GB: 2-of-11 2.4 GB: 3-of-11 2.4 GB: 4-of-11 2.4 GB: 5-of-11 2.4 GB: 6-of-11 2.4 GB: 7-of-11 2.4 GB: 8-of-11 2.4 GB: 9-of-11 2.4 GB: 10-of-11 0.1 GB: 11-of-11
Supported Languages	en
Model Architecture	Gemma4UnifiedForConditionalGeneration
License	cc-by-nc-4.0
Transformers Version	5.10.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Onca 3.0 12B 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 Onca 3.0 12B

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 4 12B It	0K / 23.9 GB	2965396	1417
Gemma 4 12B	0K / 23.9 GB	69628	816
...able5 Composer2.5 V2.3.5x Tau2	0K / 23.9 GB	242415	87
Jev Omni	0K / 23.9 GB	0	223
Gemma 4 12B It	0K / 23.9 GB	146843	15
Gemma 4 12B It NVFP4	0K / 9.3 GB	47579	20
Gemma 4 12B Aether	0K / 23.9 GB	346	0
...le5 Composer2.5 V1 Abliterated	0K / 24 GB	30003	1
Luna Gemma 12B Merged	0K / 10.4 GB	378	0
Basal Omni 1.0 Max	0K / 23.9 GB	1098	3

Note: green Score (e.g. "73.2") means that the model is better than Joesh1/onca-3.0-12b.