What are the hardware requirements for Translategemma 27B It Exl3 6bpw?

Translategemma 27B It Exl3 6bpw requires approximately 24 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Translategemma 27B It Exl3 6bpw and how large is it?

Translategemma 27B It Exl3 6bpw is developed by gkubon, a model with 27b 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 Translategemma 27B It Exl3 6bpw?

Translategemma 27B It Exl3 6bpw is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Translategemma 27B It Exl3 6bpw by gkubon — VRAM 24GB

Name: Translategemma 27B It Exl3 6bpw
Author: gkubon

Translategemma 27B It Exl3 6bpw is an open-source language model by gkubon. Features: 27b LLM, VRAM: 24GB, License: gemma, LLM Explorer Score: 0.27.

27b 6-bit Base model:google/translategem... Base model:quantized:google/tr... En Exl3 Exllamav3 Gemma3 Image-text-to-text Multilingual Region:us Safetensors Sharded Tensorflow Translation

Model Card on HF 🤗: https://huggingface.co/gkubon/translategemma-27b-it-exl3-6bpw

Translategemma 27B It Exl3 6bpw Parameters and Internals

LLM Name	Translategemma 27B It Exl3 6bpw
Repository 🤗	https://huggingface.co/gkubon/translategemma-27b-it-exl3-6bpw
Base Model(s)	Translategemma 27B It google/translategemma-27b-it
Model Size	27b
Required VRAM	24 GB
Updated	2026-10-22
Maintainer	gkubon
Model Type	gemma3
Model Files	8.4 GB: 1-of-3 8.4 GB: 2-of-3 7.2 GB: 3-of-3
Supported Languages	en
Model Architecture	Gemma3ForConditionalGeneration
License	gemma
Transformers Version	4.57.3
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Translategemma 27B It Exl3 6bpw 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 Translategemma 27B It Exl3 6bpw

Best Alternatives	Context / RAM	Downloads	Likes
Fallen Gemma3 27B V1	128K / 55.3 GB	90	49
Gemma 3 27B It	0K / 55.3 GB	769066	2006
Gemma 3 27B It	0K / 55.3 GB	42790	16
Translategemma 27B It	0K / 55.3 GB	16445	390
SAEVerbalizer 27B	0K / 55.3 GB	445	0
Gemma 3 27B It Quantized.w4a16	0K / 19.8 GB	329829	13
MamayLM Gemma 3 27B IT V2.0	0K / 55.2 GB	1875	8
BgGPT Gemma 3 27B IT	0K / 55.3 GB	3767	11
Vllm Translategemma 27B It	0K / 55.3 GB	2599	13
Medgemma 27B It Heretic	0K / 55.3 GB	14	0

Note: green Score (e.g. "73.2") means that the model is better than gkubon/translategemma-27b-it-exl3-6bpw.