What are the hardware requirements for Paligemma2 3B Ft Docci 448 Bf16?

Paligemma2 3B Ft Docci 448 Bf16 requires approximately 6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Paligemma2 3B Ft Docci 448 Bf16 and how large is it?

Paligemma2 3B Ft Docci 448 Bf16 is developed by mlx-community, a model with 3b 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 Paligemma2 3B Ft Docci 448 Bf16?

Paligemma2 3B Ft Docci 448 Bf16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Paligemma2 3B Ft Docci 448 Bf16 by mlx-community — VRAM 6GB

Name: Paligemma2 3B Ft Docci 448 Bf16
Author: mlx-community

Paligemma2 3B Ft Docci 448 Bf16 is an open-source language model by mlx-community. Features: 3b LLM, VRAM: 6GB, License: gemma.

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

Model Card on HF 🤗: https://huggingface.co/mlx-community/paligemma2-3b-ft-docci-448-bf16

Paligemma2 3B Ft Docci 448 Bf16 Parameters and Internals

LLM Name	Paligemma2 3B Ft Docci 448 Bf16
Repository 🤗	https://huggingface.co/mlx-community/paligemma2-3b-ft-docci-448-bf16
Model Size	3b
Required VRAM	6 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	paligemma
Model Files	5.3 GB: 1-of-2 0.7 GB: 2-of-2
Model Architecture	PaliGemmaForConditionalGeneration
License	gemma
Transformers Version	4.47.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Torch Data Type	bfloat16

Rank the Paligemma2 3B Ft Docci 448 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 Paligemma2 3B Ft Docci 448 Bf16

Best Alternatives	Context / RAM	Downloads	Likes
Paligemma 3B Ft Cococap 448	0K / 11.7 GB	231181	3
Paligemma 3B Ft Vqav2 448	0K / 11.7 GB	111	18
Paligemma2 3B Pt 896 4bit	0K / 1.7 GB	37	1
Paligemma2 3B Mix 224 4bit	0K / 2.3 GB	54	1
Paligemma 3B Mix 448 8bit	0K / 3.1 GB	121	7

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/paligemma2-3b-ft-docci-448-bf16.