# Depth-Anything-V2-Small-hf by Depth Aything: Open Model Source: https://savrn.com/models/depth-anything-v2-small-hf Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve Depth-Anything-V2-Small-hf (25M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.0 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 24, 2026. [Depth-Anything-V2-Small-hf on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/depth-anything-v2-small-hf/gpus) ## SAVRN's Notes on Depth-Anything-V2-Small-hf Ninety-nine megabytes on disk is the whole download, and at 16-bit the memory needed rounds to 0.1 GB. The cheapest setup our Index lists, one MI300X with 192 GB at $1.85 per hour on-demand, carries roughly two thousand times that: nobody buys a GPU for this model. Depth Anything V2 Small takes one image and returns a depth map, and it lives in whatever memory is left on a card already doing other work. Apache 2.0 lets you ship it inside a commercial product, fine-tune it and redistribute the result, provided the notices travel with it and significant changes are stated. Access is open. No context length applies because the input is pixels, not tokens, and no Index host prices it, so it costs only the hardware minutes it borrows. Two arXiv papers describe it, 2406.09414 and 2401.10891, and the checkpoint has not changed since July 5, 2024. SAVRN Research, 2026-09-18 ## Model Card By Depth Aything, published under apache-2.0, revision 5426e4f0f365. ### Depth Anything V2 Small – Transformers Version Depth Anything V2 is trained from 595K synthetic labeled images and 62M+ real unlabeled images, providing the most capable monocular depth estimation (MDE) model with the following features: - more fine-grained details than Depth Anything V1 - more robust than Depth Anything V1 and SD-based models (e.g., Marigold, Geowizard) - more efficient (10x faster) and more lightweight than SD-based models - impressive fine-tuned performance with our pre-trained models This model checkpoint is compatible with the transformers library. [Read the full model card (430 words)](https://savrn.com/models/depth-anything-v2-small-hf/card) ## Configuration Architecture DepthAnythingForDepthEstimation Stored precision float32 Model type depth_anything ## Identity and Version Repository depth-anything/Depth-Anything-V2-Small-hf Publisher Depth Aything Task Depth estimation Modality Other Library transformers Parameters 25M parameters Languages Not stated by the source Revision 5426e4f0f36572d16453bbda7a8389317b1bef99 First published 2024-06-18 Last updated 2024-07-05 ## Files and Weights 5 files, 99.2 MB in total. The weights are 1 file totalling 99.2 MB in safetensors. Weights1 file · 99.2 MB Configuration2 files · 1.7 KB Documentation1 file · 4.4 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 99.2 MB | 3152477ce0d8 | | config.json | Configuration | 950 B | — | | preprocessor_config.json | Configuration | 775 B | — | | README.md | Documentation | 4.4 KB | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 99.2 MB [Download from Depth Aything](https://huggingface.co/depth-anything/Depth-Anything-V2-Small-hf) Released by Depth Aything through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by arXiv:2401.10891 - Described by arXiv:2406.09414 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 99.2 MB | | 16-bit | 0.0 GB | | 8-bit | 0.0 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Built on This Model - Quantized from[truecal-portion-encoder](https://savrn.com/models/truecal-portion-encoder) - Derived from[truecal-portion-encoder](https://savrn.com/models/truecal-portion-encoder) ## Questions About Depth-Anything-V2-Small-hf ### How much GPU memory does Depth-Anything-V2-Small-hf need? About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (25M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run Depth-Anything-V2-Small-hf on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use Depth-Anything-V2-Small-hf commercially? Yes. Depth-Anything-V2-Small-hf is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ## Similar Models Model · Depth estimation ### [dpt-hybrid-midas](https://savrn.com/models/dpt-hybrid-midas) [Intel](https://savrn.com/model-publishers/intel) Dense Prediction Transformer (DPT) model trained on 1.4 million images for monocular depth estimation. It was introduced in the paper Vision Transformers for Dense Prediction by Ranftl et al. (2021) and first released in this repository. DPT uses the Vision Transformer (ViT) as backbone and adds a neck + head on top for monocular depth estimation. This repository hosts the "hybrid" version of the model as stated in the paper. DPT-Hybrid diverges from DPT by using ViT-hybrid as a backbone and taking some activations from the backbone. The model card has been written in combination by the Hugging Face team and Intel. Here is how to use this model for zero-shot depth estimation on an image… Open weights apache-2.0 transformers [View model](https://savrn.com/models/dpt-hybrid-midas) Model · Depth estimation ### [Depth-Anything-3-Small-LiteRT](https://savrn.com/models/depth-anything-3-small-litert) [LiteRT Community (FKA TFLite)](https://savrn.com/model-publishers/litert-community) On-device LiteRT / TFLite conversion of Depth Anything 3 — Small (ByteDance-Seed, Apache-2.0) for monocular depth, running fully on the mobile GPU via the LiteRT CompiledModel API (ML Drift delegate). No CPU fallback ops — the whole graph is GPU-compatible. DA3 processes images at their native aspect ratio (upperboundresize, longer side → 896, multiple of 14). Forcing a square 896×896 and letterbox-padding drops the match to corr 0.977 (the black padding leaks into the content through global attention). Converting at the native rectangle restores corr 0.9994 and is also faster (fewer tokens). This checkpoint is built for portrait ~9:16. For another aspect, re-convert at that shape (or your… Open weights apache-2.0 litert [View model](https://savrn.com/models/depth-anything-3-small-litert) Model · Depth estimation ### [RK182X-DEPTH-DA3-BASE](https://savrn.com/models/rk182x-depth-da3-base) [RKNNAI](https://savrn.com/model-publishers/rknnai) 本仓库提供由 depth-anything/DA3-BASE 转换的 RKNN 模型。 - Model ID：RKNNAI/RK182X-DEPTH-DA3-BASE - 模型显示名称：RK182X-DEPTH-DA3-BASE - 源模型：depth-anything/DA3-BASE - 模型类型：DEPTH ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：Apache License 2.0，正文见 LICENSE，归属与转换修改说明见 NOTICE。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本包不包含运行库。 Open weights apache-2.0 [View model](https://savrn.com/models/rk182x-depth-da3-base) Model · Depth estimation ### [GRADE](https://savrn.com/models/grade) [Physical Intelligence Rice](https://savrn.com/model-publishers/phi-lab-rice) This repository contains the complete GRADE model, paper ablations, and baselines: 19 model checkpoint files plus one auxiliary TAESD weight file (20.safetensors files in total). It also includes the inference and metric code and the saved camera-ready quantitative results. The full GRADE model uses the radar, diffusion, and ControlNet checkpoints in checkpoints/grade/. - E1 — saved-result reproduction: regenerate the quantitative tables and figures from the supplied camera-ready CSVs and auxiliary evaluation data. This requires no inference or dataset download. - E2 — local reproduction: run inference on the released evaluation data, compute 2D/3D metrics, then regenerate the quantitative… Open weights cc-by-nc-4.0 pytorch [View model](https://savrn.com/models/grade) Model · Depth estimation ### [iris-3b](https://savrn.com/models/iris-3b) [Henry Lee](https://savrn.com/model-publishers/nynxz) ComfyUI-ready files for Iris-3B by Speridlabs, a 3B text-to-image transformer that works directly in pixel space (no VAE). Use them with ComfyUI-Iris. It adds native Iris support without any custom nodes and has an example workflow for each file below. qwen3vl4bbf16.safetensors from Comfy-Org/Qwen3-VL. Load it with Load CLIP, type krea2. Text to image. Load Diffusion Model, Load CLIP (krea2), Load VAE (pixelspace), Empty Latent Image at about 1 megapixel, and an empty negative prompt. resmultistep or euler, simple, 50 steps, CFG 3. Upscale x4. Base model plus the upscaler LoRA. Scale the image up 4x with bicubic, VAE Encode, multiply the latent by 2 (LatentMultiply), then one… Open weights apache-2.0 [View model](https://savrn.com/models/iris-3b) Model · Depth estimation ### [SemiSupMDE](https://savrn.com/models/semisupmde) [Amir El-Ghoussani](https://savrn.com/model-publishers/amirmael) Models for the paper Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation (CoLLAs 2024) by Amir El-Ghoussani, Julia Hornauer, Gustavo Carneiro and Vasileios Belagiannis. Code: github.com/AmirMaEl/SemiSupMDE. A single U-Net (54.6M parameters) predicts depth from one RGB image. It is trained on synthetic Virtual KITTI with ground truth and adapted to real KITTI without any KITTI labels, using a pairwise loss on source images and a perturbation-consistency loss across RandAugment views of the unlabelled target images. Both checkpoints are PyTorch state dicts. KITTI Eigen test split (697 images), Garg crop, velodyne ground truth, no median scaling: With… Open weights pytorch [View model](https://savrn.com/models/semisupmde) ## Depth Aything [All models and datasets](https://savrn.com/model-publishers/depth-anything) ## Versions - [5426e4f0f365](https://savrn.com/models/depth-anything-v2-small-hf/versions/5426e4f0f365) · current 2026-10-24 ## Explore More - [All depth estimation models](https://savrn.com/models/tasks/depth-estimation) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-19. - [Hugging Face record](https://huggingface.co/depth-anything/Depth-Anything-V2-Small-hf) - [How the hub is built](https://savrn.com/model-hub/methodology)