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
405 K
Likes
75
Download history
daily snapshots · 54 days
▲ 11.9 M in the last 30 days (96.7%)
12.3 M405 K
Oct 12Oct 22Nov 1Nov 10
12.3 M405 K
Sep 18Oct 6Oct 24Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict 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