What are the hardware requirements for Gemma 2 27B 4bit?

Gemma 2 27B 4bit requires approximately 15.3 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma 2 27B 4bit and how large is it?

Gemma 2 27B 4bit 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.

How does Gemma 2 27B 4bit perform on standard benchmarks?

Gemma 2 27B 4bit has the following published scores: LMSYS ELO 1289. Compare against reference models on this page or on the LLM Explorer leaderboards.

Gemma 2 27B 4bit by mlx-community — VRAM 15.3GB, 8K context

Name: Gemma 2 27B 4bit
Author: mlx-community

Gemma 2 27B 4bit is an open-source language model by mlx-community. Features: 27b LLM, VRAM: 15.3GB, Context: 8K, License: gemma, Quantized, LLM Explorer Score: 0.26, ELO: 1289.

4bit Endpoints compatible Gemma2 Mlx Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/gemma-2-27b-4bit

Gemma 2 27B 4bit Benchmarks

LMSys ELO 1289 vs 1272 (so35) 1.3%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Gemma 2 27B 4bit Parameters and Internals

Model Type

text-generation

Additional Notes

Model was converted to MLX format using mlx-lm version 0.15.0.

LLM Name	Gemma 2 27B 4bit
Repository 🤗	https://huggingface.co/mlx-community/gemma-2-27b-4bit
Base Model(s)	Gemma 2 27B It google/gemma-2-27b-it
Model Size	27b
Required VRAM	15.3 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	gemma2
Model Files	5.3 GB: 1-of-3 5.3 GB: 2-of-3 4.7 GB: 3-of-3
Quantization Type	4bit
Model Architecture	Gemma2ForCausalLM
License	gemma
Context Length	8192
Model Max Length	8192
Transformers Version	4.42.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	256000
Torch Data Type	float32

Rank the Gemma 2 27B 4bit 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 2 27B 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 2 27B 8bit	8K / 28.8 GB	11	2
Gemma2 Mixed Therapy Ft	8K / 15.8 GB	5	2
Gemma 2 27B It Bnb 4bit	8K / 15.8 GB	830	11
GEMMA2 27B NLI 16bit	8K / 54.7 GB	23	0
Gemma 2 27B It 4bit	8K / 15.3 GB	372	8
Gemma 2 27B It 8bit	8K / 28.8 GB	152	10
Gemma 2 27B Bnb 4bit	8K / 15.8 GB	90	13
Gemma 2 27B It 4bit	8K / 15.8 GB	20	3
ATOMIS	32K / 66 GB	7	8
SystemGemma2 27B It	32K / 54.7 GB	96	1

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gemma-2-27b-4bit.