What are the hardware requirements for Gemma 3 27B Pt Bf16?

Gemma 3 27B Pt Bf16 requires approximately 57.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma 3 27B Pt Bf16 and how large is it?

Gemma 3 27B Pt Bf16 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 Gemma 3 27B Pt Bf16?

Gemma 3 27B Pt Bf16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gemma 3 27B Pt Bf16 by mlx-community — VRAM 57.7GB

Name: Gemma 3 27B Pt Bf16
Author: mlx-community

Gemma 3 27B Pt Bf16 is an open-source language model by mlx-community. Features: 27b LLM, VRAM: 57.7GB, License: gemma.

Endpoints compatible Gemma3 Image-text-to-text Mlx Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/gemma-3-27b-pt-bf16

Gemma 3 27B Pt Bf16 Parameters and Internals

LLM Name	Gemma 3 27B Pt Bf16
Repository 🤗	https://huggingface.co/mlx-community/gemma-3-27b-pt-bf16
Model Size	27b
Required VRAM	57.7 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	gemma3
Model Files	5.3 GB: 1-of-11 5.3 GB: 2-of-11 5.2 GB: 3-of-11 5.3 GB: 4-of-11 5.2 GB: 5-of-11 5.2 GB: 6-of-11 5.3 GB: 7-of-11 5.2 GB: 8-of-11 5.2 GB: 9-of-11 5.3 GB: 10-of-11 5.2 GB: 11-of-11
Model Architecture	Gemma3ForConditionalGeneration
License	gemma
Transformers Version	4.50.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Torch Data Type	bfloat16

Rank the Gemma 3 27B Pt Bf16 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 Gemma 3 27B Pt Bf16

Best Alternatives	Context / RAM	Downloads	Likes
Fallen Gemma3 27B V1	128K / 55.3 GB	90	49
Big Tiger Gemma 27B V3	0K / 55.3 GB	172	57
Gemma 3 R1 27B V1	0K / 55.3 GB	2	26
CardProjector 27B V4	0K / 55.3 GB	109	27
CardProjector 27B V4	0K / 55.3 GB	27	35
MamayLM Gemma 3 27B IT V2.0	0K / 55.2 GB	1875	8
Medgemma 27B It Bf16	0K / 57.7 GB	175	4
Gemma 3 27B It Qat Bf16	0K / 57.7 GB	114	6
Gemma 3 27B It Bf16	0K / 57.7 GB	63	5
Translategemma 27B It 8bit	0K / 28.8 GB	467	5

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gemma-3-27b-pt-bf16.