What are the hardware requirements for Sorjin2 12B Instruct?

Sorjin2 12B Instruct requires approximately 23.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Sorjin2 12B Instruct and how large is it?

Sorjin2 12B Instruct is developed by muzaffercky, 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 Sorjin2 12B Instruct?

Sorjin2 12B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sorjin2 12B Instruct by muzaffercky — VRAM 23.9GB

Name: Sorjin2 12B Instruct
Author: muzaffercky

Sorjin2 12B Instruct is an open-source language model by muzaffercky. Features: 12b LLM, VRAM: 23.9GB, Instruction-Based, LLM Explorer Score: 0.25.

Base model:finetune:google/gem... Base model:google/gemma-4-12b-... Chat Continual-pretraining Conversational Dataset:huggingfacefw/fineweb-... Dataset:huggingfacefw/fineweb-... Dataset:muzaffercky/kurdish-th... En Endpoints compatible Gemma4 unified Image-text-to-text Instruct Kmr Ku Kurdish Kurmanji Lora Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/muzaffercky/Sorjin2-12B-Instruct

Sorjin2 12B Instruct Parameters and Internals

LLM Name	Sorjin2 12B Instruct
Repository 🤗	https://huggingface.co/muzaffercky/Sorjin2-12B-Instruct
Base Model(s)	Gemma 4 12B It muzaffercky/Sorjin2-LoRA google/gemma-4-12B-it muzaffercky/Sorjin2-LoRA
Model Size	12b
Required VRAM	23.9 GB
Updated	2026-10-31
Maintainer	muzaffercky
Model Type	gemma4_unified
Instruction-Based	Yes
Model Files	23.9 GB
Supported Languages	ku en
Model Architecture	Gemma4UnifiedForConditionalGeneration
Transformers Version	5.19.0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
LoRA Model	Yes

Rank the Sorjin2 12B Instruct 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 Sorjin2 12B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Grug 12B	0K / 23.9 GB	519	67
Gemma 4 12B It Esper4	0K / 23.9 GB	422	10
Gemma 4 12B It Guardpoint	0K / 23.9 GB	75	4
Gemma 4 12B It Tachibana Agent	0K / 23.9 GB	82	3

Note: green Score (e.g. "73.2") means that the model is better than muzaffercky/Sorjin2-12B-Instruct.