NEWVectors or files. Pick a path.Start →

    Models

    Every model Mixpeek runs, calls or can load: what it is good and bad at, its inputs and outputs, how it runs with scale to zero, its license, and the templates that use it. Ordered by use. Filter by anything on the record; the address bar keeps the filter so you can share it.

    91 models

    Templates models.json

    Recommended by use case

    Task: Segmentation

    9 of 91 models

    Hardware, cost and evidence come from each record. "Unmeasured" means we have not measured it on our own image yet.

    • Runs as a custom plugin

      SAM 2.1 Hiera Tiny (small, base-plus)

      Segmentation · facebook/sam2.1-hiera-tiny

      Fast promptable masks; the size to try on CPU for image masks from detector boxes.

      • In/out Image, Video to Masks, Scores, Tracks
      License
      Apache-2.0
      Hardware
      Runs on CPU
      Recommended
      Yes
      View modelJSON
    • Runs as a custom plugin

      SAM 2.1 Hiera Large

      Segmentation · facebook/sam2.1-hiera-large

      Highest-quality promptable masks in images and video, with memory-based tracking of an object across frames.

      • In/out Image, Video to Masks, Scores, Tracks
      License
      Apache-2.0
      Hardware
      Needs a GPU
      View modelJSON
    • Not runnable today

      EfficientSAM ViT-S

      Segmentation · yformer/EfficientSAM (efficient_sam_vits.pt)

      SAM-style point and box prompted masks at a fraction of SAM ViT-H cost (masked-image pretraining distillation).

      • In/out Image to Masks, Scores
      License
      Apache-2.0
      Hardware
      Runs on CPU
      View modelJSON
    • Not runnable today

      MobileSAM

      Segmentation · dhkim2810/MobileSAM (mobile_sam.pt)

      SAM with a 5M-parameter TinyViT encoder: box or point prompted masks on CPU in tens of milliseconds.

      • In/out Image to Masks, Scores
      License
      Apache-2.0
      Hardware
      Runs on CPU
      View modelJSON
    • Not runnable today

      SAM 3 (Segment Anything with Concepts)

      Segmentation · facebook/sam3

      Segments and tracks every instance of a concept named by a short noun phrase or an exemplar image ('yellow school bus'), across images and video.

      • In/out Image, Video, Text to Masks, Boxes, Scores, Tracks
      License
      SAM License
      Hardware
      Needs a GPU
      View modelJSON
    • Not runnable today

      Ultralytics YOLO11 segment

      Segmentation · Ultralytics/YOLO11 (yolo11n-seg.pt)

      Fast segment for the fixed COCO label set; n size runs in real time on CPU.

      • In/out Image to Boxes, Masks, Labels, Scores
      License
      AGPL-3.0
      Hardware
      Runs on CPU
      View modelJSON
    • Not runnable today

      Ultralytics YOLO26 segment

      Segmentation · Ultralytics/YOLO26 (yolo26n-seg.pt)

      Fast segment for the fixed COCO label set; n size runs in real time on CPU.

      • In/out Image to Boxes, Masks, Labels, Scores
      License
      AGPL-3.0
      Hardware
      Runs on CPU
      View modelJSON
    • Not runnable today

      Ultralytics YOLOv8 segment

      Segmentation · Ultralytics/YOLOv8 (yolov8n-seg.pt)

      Fast segment for the fixed COCO label set; n size runs in real time on CPU.

      • In/out Image to Boxes, Masks, Labels, Scores
      License
      AGPL-3.0
      Hardware
      Runs on CPU
      View modelJSON
    • Not runnable today

      YOLOE-11 (text, visual and prompt-free)

      Segmentation · yoloe-11s-seg.pt

      Open-vocabulary detection and segmentation from text, an example image, or no prompt (prompt-free variant names objects from a built-in vocabulary).

      • In/out Image, Text to Boxes, Masks, Labels, Scores
      License
      AGPL-3.0
      Hardware
      Runs on CPU
      View modelJSON

    Questions

    Which of these models does Mixpeek run today?
    15 are served on Mixpeek as Ray Serve apps that start at zero replicas and wake on first use (Multilingual E5 Large Instruct, all-MiniLM-L6-v2, SigLIP Base patch16 224, InsightFace buffalo_l (SCRFD-10GF + ArcFace ResNet50 WebFace600K), InsightFace buffalo_sc (SCRFD-500MF + MobileFaceNet WebFace600K) and others). 13 are provider APIs Mixpeek calls by name. 34 can run as a custom plugin and do not run yet. 29 are blocked today; each page says why.
    How is the default order decided?
    By usage, the namespaces and collections that use each model, counted on 2026-11-06T13:42:25Z, then by how many templates use it, whether it runs today and whether we have our own evaluation.
    What does unmeasured mean on a model?
    We have not measured that model's cost or quality on our own image and data yet. Publisher benchmarks are linked from the model's sources and are not copied into the measured fields.
    Can an agent read this catalog?
    Yes. /models.json holds every record and /models/<id>.json holds one. They are the same records this page renders, generated from the catalog the Mixpeek server is built from.
    How do I use a model in a namespace?
    Open the model and deploy a template that already uses it, or add it to a new or existing namespace from the Designer in Studio. Every served model starts at zero replicas, so an idle namespace costs nothing for inference.

    Hugging Face model directory

    Directory pages for 422 public models. They are not in the catalog above, and Mixpeek does not run them as listed.