DA3-BASE
depth-anythingapache-2.0vision

DA3-BASE

Updated Nov 13, 2026
Parameters
0.14B
Context
8,192
License
apache-2.0
Updated
Nov 13, 2026

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at FP16
4 of 4 quantizations fit DA3-BASE with real runtime overhead.
Q4_K_M
1 GB
Q5_K_M
1 GB
Q8_0
1 GB
FP16
1 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve depth-anything/DA3-BASE

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

DA3-BASE is an open-weight 3D generation model from depth-anything, published on Hugging Face in November 2025. It has 140M parameters and is released under the apache-2.0 license.

HardwareLink to this section

At full FP16 precision the weights need about 1 GB of memory; 8-bit quantization brings that to roughly 1 GB. That is small enough for most consumer GPUs, Apple Silicon Macs, and many CPUs.

PopularityLink to this section

DA3-BASE had 92,617 downloads on Hugging Face in the last month and has 47 likes.

Run it locallyLink to this section

The weights are on Hugging Face. Follow the model card for the exact setup and license terms.

Frequently asked

Quick answers to common questions

How much VRAM does DA3-BASE need?

DA3-BASE with 0.14B parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is DA3-BASE better than other depth-anything models?

DA3-BASE has 0.14B parameters with 8,192 context - a strong choice for 3d-generation.

What license is DA3-BASE under?

DA3-BASE is released under the apache-2.0 license, making it suitable for most commercial and personal projects.

What hardware runs DA3-BASE well?

With 0.14B parameters, DA3-BASE requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for DA3-BASE?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

What models compete with DA3-BASE?

DA3-BASE competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec