Qwen-Drive-1.0-4B

by nkasmanoffco.huggingface.nkasmanoff/qwen-drive-1-vqa-demo

Driving VQA, 3D boxes and planning with Qwen-Drive-1.0

  • Remote endpoint
  • 3 tools
  • APACHE-2.0

Uptime

Checked  · every day

100%from 5 days of checks

Up without downtime on 4 of 4 days with data.

  • No downtime
  • Degraded
  • Down over 5 minutes
  • No data
  • Not checked yet

Response time

Median 1165 ms, slowest 5% 1263 ms for the handshake and the tool list, over 30 days.

1500 ms750 ms0

How far each check got

  • Reached the address 100%
  • Completed the handshake 100%
  • Listed its tools 100%

3 tools at the last answer.

Every day
DayResultChecksMedian
4 Nov (today)No verdict yet0–
3 NovNo downtime1of 11165 ms
2 NovNo downtime1of 11002 ms
1 NovNo downtime1of 11111 ms
31 OctNo downtime21200 ms

A failure counts as down time only when a second check five minutes later fails too. How we check

Connect to the publisher's own endpoint

Add to ~/.config/eca/config.json (global) or .eca/config.json in the project:

{
  "mcpServers": {
    "qwen-drive-1-vqa-demo": {
      "url": "https://nkasmanoff-qwen-drive-1-vqa-demo.hf.space/gradio_api/mcp/sse"
    }
  }
}
For agents: the install prompt

Every step above as one Markdown text, for an assistant installing it for you.

# Install the MCP server Qwen-Drive-1.0-4B (`co.huggingface.nkasmanoff/qwen-drive-1-vqa-demo`)

Its page: https://plug.directory/servers/co.huggingface.nkasmanoff/qwen-drive-1-vqa-demo

It runs on the publisher's servers; the client connects to its URL.

Use the section for the person's client.

## Claude Desktop

Paste into Settings › Connectors › Add custom connector:

```text
https://nkasmanoff-qwen-drive-1-vqa-demo.hf.space/gradio_api/mcp/sse
```

## Claude Code

Run in a terminal:

```sh
claude mcp add --transport sse qwen-drive-1-vqa-demo https://nkasmanoff-qwen-drive-1-vqa-demo.hf.space/gradio_api/mcp/sse
```

## Cursor, Devin Desktop, LM Studio, Gemini CLI, oterm, ECA

Merge into the place for the person's client:

- Cursor: ~/.cursor/mcp.json
- Devin Desktop: ~/.config/devin/mcp_config.json
- LM Studio: mcp.json (Program › Install › Edit mcp.json)
- Gemini CLI: ~/.gemini/settings.json
- oterm: config.json in oterm's data folder (~/Library/Application Support/oterm on macOS, ~/.local/share/oterm on Linux, %APPDATA%\oterm on Windows)
- ECA: ~/.config/eca/config.json (global) or .eca/config.json in the project

```json
{
  "mcpServers": {
    "qwen-drive-1-vqa-demo": {
      "url": "https://nkasmanoff-qwen-drive-1-vqa-demo.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## VS Code

Merge into .vscode/mcp.json:

```json
{
  "servers": {
    "qwen-drive-1-vqa-demo": {
      "type": "sse",
      "url": "https://nkasmanoff-qwen-drive-1-vqa-demo.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Zed

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Cline, AnythingLLM, Augment Code

Merge into the place for the person's client:

- Cline: cline_mcp_settings.json (MCP Servers › Configure › Configure MCP Servers)
- AnythingLLM: anythingllm_mcp_servers.json in the AnythingLLM storage plugins directory
- Augment Code: Augment Settings Panel – MCP section – Import from JSON (VS Code extension)

```json
{
  "mcpServers": {
    "qwen-drive-1-vqa-demo": {
      "type": "sse",
      "url": "https://nkasmanoff-qwen-drive-1-vqa-demo.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Continue

Merge into ~/.continue/config.yaml:

```yaml
mcpServers:
  - name: "qwen-drive-1-vqa-demo"
    type: sse
    url: "https://nkasmanoff-qwen-drive-1-vqa-demo.hf.space/gradio_api/mcp/sse"
```

## Goose

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Codex

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## mcp-client-cli, TUUI, BoltAI, Bob Shell, Kiro, Kiro CLI

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Agenvoy

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Amp

Merge into ~/.config/amp/settings.json (user) or .amp/settings.json (workspace):

```json
{
  "amp.mcpServers": {
    "qwen-drive-1-vqa-demo": {
      "url": "https://nkasmanoff-qwen-drive-1-vqa-demo.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

Then restart the client, or reload its MCP servers, and ask it to list the server's tools to confirm it started.

Tools 3

  • qwen_drive_1_vqa_demo_answer_question Answer a free-form question about a driving-scene image with Qwen-Drive-1.0's VLM. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: The model's answer as plain text.
  • qwen_drive_1_vqa_demo_detect_boxes Detect 3D objects in a bundled surround-camera frame and render the summary. One forward pass of the shared VLM feeds the BEV head set, which predicts 3D boxes, an occupancy grid and a BEV map segmentation in a single frame. The official renderer plots the predicted boxes projected onto every camera and in the bird's-eye view, next to the recorded ground truth in green. Returns: The rendered summary image (RGB) and a one-line detection summary.
  • qwen_drive_1_vqa_demo_plan_scene Plan future ego trajectories for a bundled driving scene. The VLM first writes a one-sentence rationale for the driving decision, then the reward-optimized Planning Expert samples 5 s of future waypoints (10 Hz) from the attention cache that generation produced. Returns: A path to the summary figure, the model's reasoning text, and the, displacement error of the first sample against the recorded human drive.

From Hugging Face Spaces. Report a problem