mudler / object-detection updated 3 months ago

locate-anything.cpp-gguf

GGUF builds of nvidia/LocateAnything-3B for locate-anything.cpp - a C++/ggml inference engine for open-vocabulary detection / visual grounding, no Python at inference time.

Params
3.8 B
Context
Downloads 30d
1.4 M
Likes
14
Licence: other Not gated GGUF View on Hugging Face ↗

Download history

tracking started — chart appears after 7 days of snapshots (3 recorded)
1.4 M downloads in the last 30 days

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
locate-anything-q4_k.gguf Q4_K 4.7 GB 6.3 GB ✅ Runs comfortably
locate-anything-q5_k.gguf Q5_K 5.1 GB 6.7 GB ✅ Runs comfortably
locate-anything-q6_k.gguf Q6_K 5.5 GB 7.1 GB ✅ Runs comfortably
locate-anything-q8_0.gguf Q8_0 6.3 GB 8.0 GB ✅ Runs comfortably
locate-anything-f16.gguf GGUF 9.2 GB 11.1 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Parameters
3.8 B
Licence
other
First seen on the Hub
2026-06-11
Base model
LocateAnything-3B
Training datasets
undisclosed
Added to our catalog
2026-09-18

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any object-detection model