What are the hardware requirements for LocateAnything 3B Bf16?

LocateAnything 3B Bf16 requires approximately 7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LocateAnything 3B Bf16 and how large is it?

LocateAnything 3B 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 LocateAnything 3B Bf16?

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

LocateAnything 3B Bf16 by mlx-community — VRAM 7GB

Name: LocateAnything 3B Bf16
Author: mlx-community

LocateAnything 3B Bf16 is an open-source language model by mlx-community. Features: 3b LLM, VRAM: 7GB, License: other, LLM Explorer Score: 0.25.

Base model:finetune:nvidia/loc... Base model:nvidia/locateanythi... Conversational Eagle En Grounding Image-text-to-text Locateanything Mlx Mlx-vlm Nvidia Object-detection Region:us Safetensors Sharded Tensorflow Vision

Model Card on HF 🤗: https://huggingface.co/mlx-community/LocateAnything-3B-bf16

LocateAnything 3B Bf16 Parameters and Internals

LLM Name	LocateAnything 3B Bf16
Repository 🤗	https://huggingface.co/mlx-community/LocateAnything-3B-bf16
Base Model(s)	LocateAnything 3B nvidia/LocateAnything-3B
Model Size	3b
Required VRAM	7 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	locateanything
Model Files	5.3 GB: 1-of-2 1.7 GB: 2-of-2
Supported Languages	en
Model Architecture	LocateAnythingForConditionalGeneration
License	other
Model Max Length	16384
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the LocateAnything 3B 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 LocateAnything 3B Bf16

Best Alternatives	Context / RAM	Downloads	Likes
LocateAnything 3B	0K / 7.7 GB	1136916	2808
...hing 3B Delivery Detector Lora	0K / 7.5 GB	9	0
LocateAnything 3B 4bit	0K / 3 GB	435	20
LocateAnything 3B 8bit	0K / 4.1 GB	193	10

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