What are the hardware requirements for Gemma 4 12B Coder Fable5 Composer2.5 8bit?

Gemma 4 12B Coder Fable5 Composer2.5 8bit requires approximately 12.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma 4 12B Coder Fable5 Composer2.5 8bit and how large is it?

Gemma 4 12B Coder Fable5 Composer2.5 8bit is developed by mlx-community, 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 Gemma 4 12B Coder Fable5 Composer2.5 8bit?

Gemma 4 12B Coder Fable5 Composer2.5 8bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gemma 4 12B Coder Fable5 Composer2.5 8bit by mlx-community — VRAM 12.6GB

Name: Gemma 4 12B Coder Fable5 Composer2.5 8bit
Author: mlx-community

Gemma 4 12B Coder Fable5 Composer2.5 8bit is an open-source language model by mlx-community. Features: 12b LLM, VRAM: 12.6GB, License: apache-2.0, Quantized, Code Generating, LLM Explorer Score: 0.33.

8-bit 8bit Base model:quantized:yuxinlu1/... Base model:yuxinlu1/gemma-4-12... Code Codegen Coding Conversational Gemma4 Gemma4 unified Image-text-to-text Mlx Quantized Reasoning Region:us Safetensors Sharded Tensorflow Thinking

Model Card on HF 🤗: https://huggingface.co/mlx-community/gemma-4-12b-coder-fable5-composer2.5-8bit

Gemma 4 12B Coder Fable5 Composer2.5 8bit Parameters and Internals

LLM Name	Gemma 4 12B Coder Fable5 Composer2.5 8bit
Repository 🤗	https://huggingface.co/mlx-community/gemma-4-12b-coder-fable5-composer2.5-8bit
Base Model(s)	yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1 yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1
Model Size	12b
Required VRAM	12.6 GB
Updated	2026-08-10
Maintainer	mlx-community
Model Type	gemma4_unified
Model Files	5.3 GB: 1-of-3 5.4 GB: 2-of-3 1.9 GB: 3-of-3
Quantization Type	8bit
Generates Code	Yes
Model Architecture	Gemma4UnifiedForConditionalGeneration
License	apache-2.0
Transformers Version	5.10.2
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Gemma 4 12B Coder Fable5 Composer2.5 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 Gemma 4 12B Coder Fable5 Composer2.5 8bit

Best Alternatives	Context / RAM	Downloads	Likes
... Coder Fable5 Composer2.5 4bit	0K / 6.7 GB	8111	38
...ble5 Composer2.5 V1 OptiQ 4bit	0K / 8.8 GB	2920	5
...Fable5 Composer2.5 V1 4bit Msq	0K / 7.5 GB	226	6
...ser2.5 V1 Abliterated 4bit Msq	0K / 7.5 GB	201	4
...le5 Composer2.5 V1 Abliterated	0K / 24 GB	30003	1
...2B Coder Fable5 Composer2.5 V1	0K / 23.9 GB	1477	58
...4 12B Coder Fable5 Composer2.5	0K / 23.8 GB	789	3
...r Fable5 Composer2.5 V1 Sft V5	0K / 23.9 GB	30	0
...le5 Composer2.5 V1 Sft V5 Grpo	0K / 23.9 GB	24	0
...r Fable5 Composer2.5 V1 Sft V4	0K / 23.9 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gemma-4-12b-coder-fable5-composer2.5-8bit.