What are the hardware requirements for GaMS3 12B Instruct?

GaMS3 12B Instruct requires approximately 23.4 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GaMS3 12B Instruct and how large is it?

GaMS3 12B Instruct is developed by cjvt, 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 GaMS3 12B Instruct?

GaMS3 12B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GaMS3 12B Instruct by cjvt — VRAM 23.4GB, 128K context

Name: GaMS3 12B Instruct
Author: cjvt

GaMS3 12B Instruct is an open-source language model by cjvt. Features: 12b LLM, VRAM: 23.4GB, Context: 128K, License: gemma, Instruction-Based, LLM Explorer Score: 0.25.

Base model:finetune:google/gem... Base model:google/gemma-3-12b-... Bs Conversational En Gemma3 text Hr Instruct Region:us Safetensors Sharded Sl Sr Tensorflow

Model Card on HF 🤗: https://huggingface.co/cjvt/GaMS3-12B-Instruct

GaMS3 12B Instruct Parameters and Internals

LLM Name	GaMS3 12B Instruct
Repository 🤗	https://huggingface.co/cjvt/GaMS3-12B-Instruct
Base Model(s)	Gemma 3 12B Pt google/gemma-3-12b-pt
Model Size	12b
Required VRAM	23.4 GB
Updated	2026-07-16
Maintainer	cjvt
Model Type	gemma3_text
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-5 4.9 GB: 2-of-5 4.9 GB: 3-of-5 4.9 GB: 4-of-5 3.8 GB: 5-of-5
Supported Languages	sl en sr hr bs
Model Architecture	Gemma3ForCausalLM
License	gemma
Context Length	131072
Model Max Length	131072
Transformers Version	4.55.2
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	262208
Torch Data Type	bfloat16

Rank the GaMS3 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 GaMS3 12B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Erebus RP 12B Instruct 2608 V1	128K / 23.4 GB	10	0
... 12B Instruct 2608 V1 Mlx 6Bit	128K / 9.6 GB	225	1

Note: green Score (e.g. "73.2") means that the model is better than cjvt/GaMS3-12B-Instruct.