A model is still running

A model is still running or downloading. Leaving will stop the current operation. Stay on this page to let it finish.

Skip to content
LocalAI.toolsBeta

Join the waitlist

Get an email when the new apps and model runs launch.

No account needed.

OlmoEarth 1.3 Desktop

Encode aligned raw Sentinel2 L2A multispectral satellite data into complete spatial embeddings and an optional relative magnitude map.

Desktop inferencePrivate · Runs on your computer
About this model

Encode aligned raw Sentinel2 L2A multispectral satellite data into complete spatial embeddings and an optional relative magnitude map.

Model released
Unknown
Source repository created
Sep 4, 2026
Model weights · FP32
785.1 MB

Best for

  • Satellite patch similarity and retrieval experiments

Keep in mind

  • Only Sentinel2 L2A has measured task quality. Sentinel1 and Landsat remain unqualified.
  • Two held-out patches from one acquisition establish narrow retrieval evidence only; no land-cover classifier or broad accuracy claim.
  • Requires exact sensor bands, raw satellite values and calendar dates; RGB photographs are not valid input.
  • Artifact license restricts military, surveillance and extractive uses; retain the full terms.
  • Current Mac public API/lifecycle/sample-array parity passes. Production app, complete backup and cold source recovery remain pending.
  • The atomic encoder returns its tensors together; the pinned runtime has no incremental task output. Streaming is unavailable.
  • MPS places the encoder on Apple GPU with implicit Torch fallback disabled; normalization, serialization and SVG presentation use CPU. GPU placement is not end-to-end GPU execution.

Processed on your deviceYour input is processed locally in the desktop app. Model and runtime files download from external hosts.

Target platforms · verification required

  • macos · aarch64, x86_64
  • windows · x86_64

Recommended configuration

FP32 · cpu (verified platform only)

Sources & technical details
Original model
https://huggingface.co/allenai/OlmoEarth-v1_3-Base
Release verification
Unknown
Release evidence
Exact checkpoint release day not established by bounded official review; repository creation is distinct.
Source updated
Oct 13, 2026
Native model files
allenai/OlmoEarth-v1_3-Base
Files updated
Oct 13, 2026
Artifact revision
9e9e918a369701c105dde7ef56789b0ff1d47f50

Desktop app

Sample result

OlmoEarth 1.3 Base Desktop

Run OlmoEarth 1.3 Desktop on your computer

Download the desktop app to load this model, provide input and view results locally.

Public desktop downloads are coming soon.

Device requirements

macOS Apple SiliconCPU / FP32Tested8.0 GiBRAM estimate
macOS Apple SiliconMPS / FP32Tested8.0 GiBRAM estimate
If your device falls short

MemoryAdvisory only: close other apps, reduce image/tile/token/batch settings or choose a smaller verified model/precision. CPU can need more RAM than GPU.

GPUIf the selected GPU runtime fails, existing CPU fallback may recover when enabled, but CPU has its own memory/runtime needs.

PlatformUse a compatible OS/architecture/runtime or another model. These estimates do not add hardware detection or block runs.

Benchmark evidence

Saved desktop measurements apply to the recorded hardware and runtime. Fallback cases report the device that actually ran; they do not prove GPU support on the requested device.

OlmoEarth 1.3 Base Desktop

4 configurations tested
Passed4
Failed0
TestedNov 16, 2026
Runtimepytorch 2.10.0

Quality criteria

{ "frozenBeforeEmbeddings": true, "task": "same-acquisition patch embedding retrieval", "reference": "ESA Sentinel-2 L2A SCL majority class, nearest-resampled independently from the input bands", "classIds": { "water": 6, "vegetation": 4 }, "minimumLabelPurity": 0.7, "training": [ "water-train", "vegetation-train" ], "heldOut": [ "water-test", "vegetation-test" ], "metric": "cosine nearest prototype on spatial-mean student_location_tokens", "requiredAccuracy": 1, "requiredCpuMpsCosine": 0.999, "limitations": "Two test patches from one Seattle acquisition, not independent regional/year/domain validation or a land-cover classifier. Training/test windows are spatially non-overlapping. Broader retrieval quality and other sensor modes remain unmeasured." }

PrecisionDeviceResultPlatformInference / load
FP32mpsAcceleratedPassedVery fastmacos · aarch6425 ms / 2794 ms
FP32mpsAcceleratedPassedFastmacos · aarch64104 ms / 2794 ms
FP32cpuPassedVery fastmacos · aarch6432 ms / 2638 ms
FP32cpuPassedVery fastmacos · aarch6434 ms / 2638 ms
Test setup & sample details
Quality gate
{ "frozenBeforeEmbeddings": true, "task": "same-acquisition patch embedding retrieval", "reference": "ESA Sentinel-2 L2A SCL majority class, nearest-resampled independently from the input bands", "classIds": { "water": 6, "vegetation": 4 }, "minimumLabelPurity": 0.7, "training": [ "water-train", "vegetation-train" ], "heldOut": [ "water-test", "vegetation-test" ], "metric": "cosine nearest prototype on spatial-mean student_location_tokens", "requiredAccuracy": 1, "requiredCpuMpsCosine": 0.999, "limitations": "Two test patches from one Seattle acquisition, not independent regional/year/domain validation or a land-cover classifier. Training/test windows are spatially non-overlapping. Broader retrieval quality and other sensor modes remain unmeasured." }
Tested
2026-11-16T17:43:57.384054+00:00
Environment
Apple M3 Max/macOS27.2; exact pinned runtime; existing mirror active. Public API timings are scoped observations; retained standalone quality/speed evidence keeps original timestamps.
Runtime
pytorch 2.10.0
Artifact revision
9e9e918a369701c105dde7ef56789b0ff1d47f50
Fixture
{
  "file": "model-samples/olmoearth-v1-3/water-test-native-input.json",
  "size": 78041,
  "sha1": "a246964c3239153b68d88546564974a808893bde",
  "sha256": "b5d08df7f5dc266ed2521ea7e805b145d484bfccb8f97d9da3d1618ec0dd8aad",
  "url": "https://assets.localai.tools/samples/v1/files/b5d08df7f5dc266ed2521ea7e805b145d484bfccb8f97d9da3d1618ec0dd8aad/water-test-native-input.json"
}
Rerun when
artifact revision; runtime version; normalization; fixture checksum; quality gate; backend behavior
Per-case quality & failure details
[
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "metric": "held-out same-acquisition retrieval accuracy",
      "score": 1,
      "scope": "Narrow two-class same-acquisition suite; exact native output parity separately passed. Training prototypes are reference construction, not independent held-out cases."
    },
    "runtime": {
      "acceleration": "cpu",
      "artifactRevision": "9e9e918a369701c105dde7ef56789b0ff1d47f50",
      "cpuThreads": 4,
      "device": "cpu",
      "durationMs": 81.009167,
      "engine": "pytorch",
      "fallback": false,
      "fallbackReason": null,
      "family": {
        "catalogId": "olmoearth-v1-3",
        "defaultModelId": "olmoearth-v1.3-base-native",
        "displayName": "OlmoEarth 1.3",
        "id": "olmoearth-v1-3",
        "variantId": "base",
        "variantName": "Base"
      },
      "implicitMpsFallback": false,
      "inferenceMs": 34.45049999572802,
      "loadMs": 2638.494917,
      "modelId": "olmoearth-v1.3-base-native",
      "modelQuantization": null,
      "placement": null,
      "precision": "fp32",
      "provider": "cpu",
      "requestedDevice": "cpu",
      "requestedPrecision": "fp32",
      "reused": false,
      "runtimePrecision": "fp32",
      "selectionReason": "Explicit device selection; actual placement is reported after inference",
      "threadControl": null,
      "version": "2.10.0",
      "visualizationMs": 0.12316599895711988,
      "grade": "good",
      "totalMs": 2672.945416995728,
      "pixelsPerSecond": 29723.806624779885,
      "actualDevice": "cpu",
      "actualPrecision": "fp32",
      "neuralExecuted": true
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "metric": "held-out same-acquisition retrieval accuracy",
      "score": 1,
      "scope": "Narrow two-class same-acquisition suite; exact native output parity separately passed. Training prototypes are reference construction, not independent held-out cases."
    },
    "runtime": {
      "acceleration": "cpu",
      "artifactRevision": "9e9e918a369701c105dde7ef56789b0ff1d47f50",
      "cpuThreads": 4,
      "device": "cpu",
      "durationMs": 77.066208,
      "engine": "pytorch",
      "fallback": false,
      "fallbackReason": null,
      "family": {
        "catalogId": "olmoearth-v1-3",
        "defaultModelId": "olmoearth-v1.3-base-native",
        "displayName": "OlmoEarth 1.3",
        "id": "olmoearth-v1-3",
        "variantId": "base",
        "variantName": "Base"
      },
      "implicitMpsFallback": false,
      "inferenceMs": 31.63170799962245,
      "loadMs": 2638.494917,
      "modelId": "olmoearth-v1.3-base-native",
      "modelQuantization": null,
      "placement": null,
      "precision": "fp32",
      "provider": "cpu",
      "requestedDevice": "cpu",
      "requestedPrecision": "fp32",
      "reused": false,
      "runtimePrecision": "fp32",
      "selectionReason": "Explicit device selection; actual placement is reported after inference",
      "threadControl": null,
      "version": "2.10.0",
      "visualizationMs": 0.10029199620475993,
      "grade": "good",
      "totalMs": 2670.1266249996224,
      "pixelsPerSecond": 32372.5800709915,
      "actualDevice": "cpu",
      "actualPrecision": "fp32",
      "neuralExecuted": true
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "metric": "held-out same-acquisition retrieval accuracy",
      "score": 1,
      "scope": "Narrow two-class same-acquisition suite; exact native output parity separately passed. Training prototypes are reference construction, not independent held-out cases."
    },
    "runtime": {
      "acceleration": "gpu",
      "artifactRevision": "9e9e918a369701c105dde7ef56789b0ff1d47f50",
      "cpuThreads": 4,
      "device": "mps",
      "durationMs": 193.54391600000002,
      "engine": "pytorch",
      "fallback": false,
      "fallbackReason": null,
      "family": {
        "catalogId": "olmoearth-v1-3",
        "defaultModelId": "olmoearth-v1.3-base-native",
        "displayName": "OlmoEarth 1.3",
        "id": "olmoearth-v1-3",
        "variantId": "base",
        "variantName": "Base"
      },
      "implicitMpsFallback": false,
      "inferenceMs": 104.12237499986077,
      "loadMs": 2794.226,
      "modelId": "olmoearth-v1.3-base-native",
      "modelQuantization": null,
      "placement": null,
      "precision": "fp32",
      "provider": "mps",
      "requestedDevice": "mps",
      "requestedPrecision": "fp32",
      "reused": false,
      "runtimePrecision": "fp32",
      "selectionReason": "Explicit device selection; actual placement is reported after inference",
      "threadControl": null,
      "version": "2.10.0",
      "visualizationMs": 0.3558329990482889,
      "grade": "good",
      "totalMs": 2898.348374999861,
      "pixelsPerSecond": 9834.581664136736,
      "actualDevice": "mps",
      "actualPrecision": "fp32",
      "neuralExecuted": true
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "metric": "held-out same-acquisition retrieval accuracy",
      "score": 1,
      "scope": "Narrow two-class same-acquisition suite; exact native output parity separately passed. Training prototypes are reference construction, not independent held-out cases."
    },
    "runtime": {
      "acceleration": "gpu",
      "artifactRevision": "9e9e918a369701c105dde7ef56789b0ff1d47f50",
      "cpuThreads": 4,
      "device": "mps",
      "durationMs": 78.01041599999999,
      "engine": "pytorch",
      "fallback": false,
      "fallbackReason": null,
      "family": {
        "catalogId": "olmoearth-v1-3",
        "defaultModelId": "olmoearth-v1.3-base-native",
        "displayName": "OlmoEarth 1.3",
        "id": "olmoearth-v1-3",
        "variantId": "base",
        "variantName": "Base"
      },
      "implicitMpsFallback": false,
      "inferenceMs": 25.151624999125488,
      "loadMs": 2794.226,
      "modelId": "olmoearth-v1.3-base-native",
      "modelQuantization": null,
      "placement": null,
      "precision": "fp32",
      "provider": "mps",
      "requestedDevice": "mps",
      "requestedPrecision": "fp32",
      "reused": false,
      "runtimePrecision": "fp32",
      "selectionReason": "Explicit device selection; actual placement is reported after inference",
      "threadControl": null,
      "version": "2.10.0",
      "visualizationMs": 0.7897920004324988,
      "grade": "good",
      "totalMs": 2819.3776249991256,
      "pixelsPerSecond": 40713.07520033413,
      "actualDevice": "mps",
      "actualPrecision": "fp32",
      "neuralExecuted": true
    }
  }
]
Release validation still required
  • Production API/app/samples/contracts pending
  • Complete dependency closure backup and forced source-outage recovery pending

Something not quite right?

Tell us what happened with OlmoEarth 1.3 Desktop. Loading, results, or the page itself—we’re here for all of it.

Attachments Optional

Up to 3 files · 50 MB each

Browser, OS, CPU/GPU, memory, screen, storage, and network details are included automatically. Model inputs, results, and browsing history are not collected.