What are the hardware requirements for Translategemma 27B It 8bit?

Translategemma 27B It 8bit requires approximately 28.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Translategemma 27B It 8bit and how large is it?

Translategemma 27B It 8bit is developed by mlx-community, 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 8bit?

Translategemma 27B It 8bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Translategemma 27B It 8bit by mlx-community — VRAM 28.8GB

Name: Translategemma 27B It 8bit
Author: mlx-community

Translategemma 27B It 8bit is an open-source language model by mlx-community. Features: 27b LLM, VRAM: 28.8GB, License: gemma, Quantized, LLM Explorer Score: 0.23.

8-bit 8bit Base model:google/translategem... Base model:quantized:google/tr... Conversational Gemma3 Mlx Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/translategemma-27b-it-8bit

Translategemma 27B It 8bit Parameters and Internals

LLM Name	Translategemma 27B It 8bit
Repository 🤗	https://huggingface.co/mlx-community/translategemma-27b-it-8bit
Base Model(s)	Translategemma 27B It google/translategemma-27b-it
Model Size	27b
Required VRAM	28.8 GB
Updated	2026-08-06
Maintainer	mlx-community
Model Type	gemma3
Model Files	5.3 GB: 1-of-6 5.3 GB: 2-of-6 5.3 GB: 3-of-6 5.3 GB: 4-of-6 5.3 GB: 5-of-6 2.3 GB: 6-of-6
Quantization Type	8bit
Model Architecture	Gemma3ForConditionalGeneration
License	gemma
Transformers Version	4.57.3
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Translategemma 27B It 8bit 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 8bit

Best Alternatives	Context / RAM	Downloads	Likes
...emma 3 27B It Unsloth Bnb 4bit	0K / 20.2 GB	5525	19
Gemma 3 27B It Bnb 4bit	0K / 16.3 GB	2744	18
... 3 27B It Qat Q4 0 Unquantized	0K / 55.3 GB	152	42
Gemma 3 27B It Qat	0K / 55.3 GB	24	3
Translategemma 27B It 4bit	0K / 15.2 GB	190	3
Medgemma 27B It 8bit	0K / 31.2 GB	199	4
Medgemma 27B It 4bit	0K / 16.9 GB	132	4
Gemma 3 27B It 4bit	0K / 16.9 GB	1578	13
Gemma 3 27B It 4bit DWQ	0K / 16 GB	86	3
Gemma 3 27B It 8bit	0K / 31.2 GB	407	7

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/translategemma-27b-it-8bit.