Qwen2-VL-2B-Instruct-GGUF

runanywhere/Qwen2-VL-2B-Instruct-GGUF

Qwen2-VL-2B-Instruct-GGUF is a image-text-to-text model from runanywhere. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for llama.cpp. The card lists the license as apache-2.0.

Qwen2-VL-2B-Instruct by Alibaba/Qwen, quantized to GGUF format for llama.cpp, packaged for use with the RunAnywhere SDK.

Downloads · 30 days

174

8% of all-time downloads

All-time downloads

2.1K

Public

Repo size

1.7 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf1.7 GB · 100%

At a glance

Task: Image-Text-to-Text
Library: llama.cpp
License: apache-2.0
Access: Public
Created: Feb 13, 2026
Updated: Feb 13, 2026
SHA: 9f746bdb

Try a prompt

Model card

From the Hugging Face model README

Qwen2-VL 2B Instruct — GGUF

Qwen2-VL-2B-Instruct by Alibaba/Qwen, quantized to GGUF format for llama.cpp, packaged for use with the RunAnywhere SDK.

Files:

Qwen2-VL-2B-Instruct-Q4_K_M.gguf — Language model (~940 MB)
mmproj-Qwen2-VL-2B-Instruct-Q8_0.gguf — Vision encoder (~676 MB)

Usage with RunAnywhere SDK

Swift (iOS / macOS)

import RunAnywhere

RunAnywhere.registerModel(
    id: "qwen2-vl-2b-instruct-q4_k_m",
    name: "Qwen2-VL 2B Instruct Q4_K_M",
    repo: "runanywhere/Qwen2-VL-2B-Instruct-GGUF",
    files: ["Qwen2-VL-2B-Instruct-Q4_K_M.gguf", "mmproj-Qwen2-VL-2B-Instruct-Q8_0.gguf"],
    framework: .llamaCpp,
    modality: .multimodal,
    memoryRequirement: 1_800_000_000
)

// VLM inference with image
let result = try await RunAnywhere.generateVLM(
    prompt: "Describe this image in detail.",
    image: imageData,
    modelId: "qwen2-vl-2b-instruct-q4_k_m"
)

Kotlin (Android / JVM)

import com.runanywhere.sdk.RunAnywhere
import com.runanywhere.sdk.models.*

RunAnywhere.registerModel(
    id = "qwen2-vl-2b-instruct-q4_k_m",
    name = "Qwen2-VL 2B Instruct Q4_K_M",
    repo = "runanywhere/Qwen2-VL-2B-Instruct-GGUF",
    files = listOf("Qwen2-VL-2B-Instruct-Q4_K_M.gguf", "mmproj-Qwen2-VL-2B-Instruct-Q8_0.gguf"),
    framework = InferenceFramework.LLAMA_CPP,
    modality = ModelCategory.MULTIMODAL,
    memoryRequirement = 1_800_000_000L
)

val result = RunAnywhere.generateVLM(
    prompt = "Describe this image in detail.",
    image = imageData,
    modelId = "qwen2-vl-2b-instruct-q4_k_m"
)

Web (TypeScript)

import { RunAnywhere, LLMFramework, ModelCategory } from '@anthropic/runanywhere-web';

RunAnywhere.registerModels([{
  id: 'qwen2-vl-2b-instruct-q4_k_m',
  name: 'Qwen2-VL 2B Instruct Q4_K_M',
  repo: 'runanywhere/Qwen2-VL-2B-Instruct-GGUF',
  files: ['Qwen2-VL-2B-Instruct-Q4_K_M.gguf', 'mmproj-Qwen2-VL-2B-Instruct-Q8_0.gguf'],
  framework: LLMFramework.LlamaCpp,
  modality: ModelCategory.Multimodal,
  memoryRequirement: 1_800_000_000,
}]);

await RunAnywhere.downloadModel('qwen2-vl-2b-instruct-q4_k_m');
await RunAnywhere.loadModel('qwen2-vl-2b-instruct-q4_k_m');

const result = await RunAnywhere.generateVLM('Describe this image in detail.', imageData, 'qwen2-vl-2b-instruct-q4_k_m');

React Native (TypeScript)

import { RunAnywhere } from 'runanywhere-react-native';

RunAnywhere.registerModel({
  id: 'qwen2-vl-2b-instruct-q4_k_m',
  name: 'Qwen2-VL 2B Instruct Q4_K_M',
  repo: 'runanywhere/Qwen2-VL-2B-Instruct-GGUF',
  files: ['Qwen2-VL-2B-Instruct-Q4_K_M.gguf', 'mmproj-Qwen2-VL-2B-Instruct-Q8_0.gguf'],
  framework: 'llamaCpp',
  modality: 'multimodal',
  memoryRequirement: 1_800_000_000,
});

const result = await RunAnywhere.generateVLM('Describe this image.', imageData, 'qwen2-vl-2b-instruct-q4_k_m');

Flutter (Dart)

import 'package:runanywhere_flutter/runanywhere_flutter.dart';

RunAnywhere.registerModel(
  id: 'qwen2-vl-2b-instruct-q4_k_m',
  name: 'Qwen2-VL 2B Instruct Q4_K_M',
  repo: 'runanywhere/Qwen2-VL-2B-Instruct-GGUF',
  files: ['Qwen2-VL-2B-Instruct-Q4_K_M.gguf', 'mmproj-Qwen2-VL-2B-Instruct-Q8_0.gguf'],
  framework: InferenceFramework.llamaCpp,
  modality: ModelCategory.multimodal,
  memoryRequirement: 1800000000,
);

final result = await RunAnywhere.generateVLM('Describe this image.', imageData, 'qwen2-vl-2b-instruct-q4_k_m');

Model Details

Property	Value
Base Model	Qwen2-VL-2B-Instruct
Parameters	2B
Quantization	Q4_K_M (~940 MB)
Vision Encoder	Q8_0 mmproj (~676 MB)
Runtime	llama.cpp (with multimodal/mtmd)
Capabilities	Image understanding, OCR, visual QA

Attribution

Original model by Qwen/Alibaba. GGUF conversion by ggml-org.

Task: Image-Text-to-Text
Library: llama.cpp
License: apache-2.0
Languages: en
Created: Feb 13, 2026
Updated: Feb 13, 2026