What are the hardware requirements for LocateAnything 3B Community FP8 Dynamic?

LocateAnything 3B Community FP8 Dynamic requires approximately 4.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LocateAnything 3B Community FP8 Dynamic and how large is it?

LocateAnything 3B Community FP8 Dynamic is developed by shadowrock-io, 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 Community FP8 Dynamic?

LocateAnything 3B Community FP8 Dynamic is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LocateAnything 3B Community FP8 Dynamic by shadowrock-io — VRAM 4.3GB

Name: LocateAnything 3B Community FP8 Dynamic
Author: shadowrock-io

LocateAnything 3B Community FP8 Dynamic is an open-source language model by shadowrock-io. Features: 3b LLM, VRAM: 4.3GB, License: other, LLM Explorer Score: 0.27.

8-bit Base model:nvidia/locateanythi... Base model:quantized:nvidia/lo... Coco Compressed-tensors Conversational Custom code Fp8 Image-text-to-text Llm-compressor Locateanything Model-index Object-detection Open-vocabulary-detection Quantized Qwen2 Region:us Safetensors Vision Vision-language Visual-grounding Vllm W8a8

Model Card on HF 🤗: https://huggingface.co/shadowrock-io/LocateAnything-3B-Community-FP8-Dynamic

LocateAnything 3B Community FP8 Dynamic Parameters and Internals

LLM Name	LocateAnything 3B Community FP8 Dynamic
Repository 🤗	https://huggingface.co/shadowrock-io/LocateAnything-3B-Community-FP8-Dynamic
Base Model(s)	LocateAnything 3B nvidia/LocateAnything-3B
Model Size	3b
Required VRAM	4.3 GB
Updated	2026-08-21
Maintainer	shadowrock-io
Model Type	locateanything
Model Files	4.3 GB
Model Architecture	LocateAnythingForConditionalGeneration
License	other
Model Max Length	16384
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Torch Data Type	bfloat16
Errors	replace

Rank the LocateAnything 3B Community FP8 Dynamic 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 Community FP8 Dynamic

Best Alternatives	Context / RAM	Downloads	Likes
LocateAnything 3B	0K / 7.7 GB	1136916	2808
...ateAnything 3B Community NVFP4	0K / 3 GB	11	1
...hing 3B Delivery Detector Lora	0K / 7.5 GB	9	0
LocateAnything 3B Bf16	0K / 7 GB	50	2
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 shadowrock-io/LocateAnything-3B-Community-FP8-Dynamic.