{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/code-sandboxes.gpu-or-special-machine/",
    "json": "https://www.anchorterminal.com/niches/code-sandboxes.gpu-or-special-machine/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/code-sandboxes.gpu-or-special-machine/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/code-sandboxes.gpu-or-special-machine/index.min.md"
  },
  "markdown": "No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 0 | 10 | 24 | 6 | 3 |\n\n## What counts as done\n\nA sandbox of the requested class starts, the code sees the GPU or desktop (nvidia-smi or a screenshot succeeds), a mounted volume or snapshot of at least 10 GB restores without error, and the hourly price is published.\n\nMeasured, for our own tests: the sandbox starts within 60 seconds.\n\nHow agents ask for it: run this training script on a GPU; test the Windows build; emulate the Android app off my laptop; run the iOS simulator somewhere else\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Agent 37 Cloud (Agent 37 Inc.)**: The agent37-android template boots an Android 14 emulator on a VM instance with a noVNC screen, and desktop templates exist, with prices published. No GPU, Windows or macOS class.\n- **Celesto (formerly SmolVM) (Celesto AI, Inc.)**: Windows 11 from your own ISO image and a macOS desktop preview boot locally with a display, and Linux desktops with Chromium. No GPU passthrough and no hosted hourly price for them.\n- **Daytona (Daytona Platforms Inc.)**: NVIDIA and AMD GPU sandboxes with published hourly prices and S3-backed volumes, Windows (Tier 3, contact support) and macOS classes. GPU sandboxes are ephemeral and spot needs Tier 2.\n- **E2B (FoundryLabs, Inc.)**: Desktop sandboxes with VNC and an Android 16 template exist with published compute rates; no GPU, Windows or macOS class.\n- **Freestyle (Freestyle Cloud Inc.)**: Nested KVM runs an Android emulator inside a Linux VM per the guides; no GPU, Windows or macOS class, and no display price.\n- **InstaVM (Checksum Labs, Inc.)**: A Linux desktop with noVNC and a headless browser are offered at the published compute rate; no GPU, Windows or macOS.\n- **Maritime (Maritime AI, Inc.)**: Linux desktops at $0.12 an hour, Windows at $0.18 (Growth plan or above) and Android phones at $0.15 with screenshots over MCP, sleeping with disk at $0.08 a GB-month. No GPU class.\n- **Modal Sandboxes (Modal Labs, Inc.)**: GPU sandboxes at Modal's per-second GPU rates, but only with the gVisor runtime and never with memory snapshots; issue 4139 hit a 256 GiB changed-data limit on filesystem snapshots.\n- **Offscreen (Mark Phelps (individual))**: A fresh macOS VM with Xcode runs XCUITest, the iOS Simulator and built apps and saves screenshots as artifacts, free. A simulator boot takes minutes, only two VMs run, and there is no GPU or Windows.\n- **Sandbox0 (Lougao, LLC)**: A chrome template gives a shared Chrome desktop; no GPU, Windows or macOS class.\n\n## Couldn't check\n\nThe docs were closed to us, or silent. These carry no mark either way.\n\n- **Runloop Devboxes (Runloop AI, Inc.)**: The docs index lists an optional GPU on devboxes, but no GPU page was read and the service is winding down.\n\n- not this job: Amazon Bedrock AgentCore Code Interpreter (Amazon Web Services, Inc.): No GPU, Windows or desktop class; every session is a Linux microVM capped at 2 vCPU.\n- not this job: Blaxel Sandboxes (Blaxel, Inc.): No GPU, Windows or desktop class; an Android-compatible kernel option runs Android in a container, not a device with a screen.\n- not this job: Cloudflare Sandbox SDK (Cloudflare, Inc.): Linux containers and Dynamic Workers only; no GPU, Windows or desktop class.\n- not this job: DeltaBox Lite (DeltaBox (delta-box)): Runs on the host it is installed on; no GPU, Windows guest or display class.\n- not this job: Deno Sandbox (Deno Land Inc.): Linux microVMs of 768 to 4096 MB only; no GPU, Windows or desktop class.\n- not this job: Microsoft Execution Containers (Microsoft Corporation): Contains code on the host it runs on; no GPU, remote Windows guest or display class.\n- not this job: Morph Cloud (Morph Labs, Inc.): No GPU, Windows or desktop class in the docs text.\n- not this job: SPACE (Perplexity AI): Firecracker Linux microVMs only; no GPU, Windows or desktop execution environment.\n- not this job: Sprites (Fly.io, Inc.): Linux microVMs with 8 vCPUs and 100 GB; no GPU, Windows or desktop class.\n- not this job: Together Code Sandbox (Together Computer, Inc.): No GPU, Windows or desktop class in the sandbox docs.\n- not this job: Vercel Sandbox (Vercel Inc.): Linux microVMs up to 32 vCPUs; no GPU, Windows or desktop class.\n\n## What stops agents finishing\n\n- GPU sandboxes only with the gVisor runtime (Modal) or ephemeral and gated to Tier 2 (Daytona spot GPUs)\n- filesystem snapshots fail above a 256 GiB changed-data limit (Modal issue 4139)\n- Windows and macOS classes are early access\n\n## Around it\n\nBefore: open-weights.pick-model, code-sandboxes.coding-agent-workspace. After: inference.serve-model, code-sandboxes.dev-server-preview.\n\n## Where this comes from\n\nWeight 6 of 100 in Code execution sandboxes: 3 of 53 mentions (an A100 Modal exec issue, a Modal snapshot size limit issue, a laptop user offloading Android emulation). Only Modal and Daytona list GPUs, so the count is small by construction.\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/code-sandboxes.gpu-or-special-machine.json, or the MCP tool get_use_case with id code-sandboxes.gpu-or-special-machine. Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Run agent code on a GPU, Windows or desktop machine",
        "url": ""
      }
    ],
    "description": "Run agent code on a GPU, Windows or desktop machine: 0 companies fully do it, 10 with a limit, 24 carry the tag. Every listing in Code execution sandboxes with the reason and a source.",
    "facts": null,
    "h1": "Run agent code on a GPU, Windows or desktop machine",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/code-sandboxes.gpu-or-special-machine/",
    "published": "",
    "section": "agents",
    "title": "Run agent code on a GPU, Windows or desktop machine | Anchor Terminal",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/code-sandboxes.gpu-or-special-machine/"
  },
  "tokens": {
    "markdown": 1550,
    "slim": 330
  },
  "version": 1
}
