InferX Catalog | InternVL3_5-38B-Instruct

InternVL3_5-38B-Instruct

InternVL3.5-38B-Instruct is an advanced multimodal large language model (MLLM) released in late 2025 by Shanghai AI Laboratory.

OpenGVLab multimodal image2text

Log in to deploy

Metadata

Provider

OpenGVLab

Modality

multimodal

API type

image2text

Source

huggingface / OpenGVLab/InternVL3_5-38B-Instruct

Created

2026-04-12 13:56:26 UTC

Updated

2026-04-13 03:07:17 UTC

Catalog version

2

Visibility

Published

Specifications

Parameters

38.00B

MoE

No

Max model length

10000

Image

vllm/vllm-openai:v0.16.0

Default Deploy Config

GPU count

2

vRAM

70000 MB

Summary

2xGPU 70000 MB

Recommended Use Cases

—

Model Spec

{
    "image": "vllm/vllm-openai:v0.16.0",
    "commands": [
        "--model",
        "OpenGVLab/InternVL3_5-38B-Instruct",
        "--trust-remote-code",
        "--max-model-len",
        "10000",
        "--tensor-parallel-size=2"
    ],
    "resources": {
        "GPU": {
            "Count": 2,
            "vRam": 70000
        }
    },
    "envs": [],
    "policy": {
        "Obj": {
            "min_replica": 0,
            "max_replica": 1,
            "standby_per_node": 1,
            "parallel": 50,
            "queue_len": 100,
            "queue_timeout": 30.0,
            "scalein_timeout": 1.0,
            "scaleout_policy": {
                "WaitQueueRatio": {
                    "wait_ratio": 0.1
                }
            },
            "runtime_config": {
                "graph_sync": false
            }
        }
    },
    "sample_query": {
        "body": {
            "max_tokens": "200",
            "temperature": "0"
        },
        "path": "v1/chat/completions",
        "prompt": "What is in this image?",
        "apiType": "image2text",
        "dataUrl": "https://www.ilankelman.org/stopsigns/australia.jpg",
        "prompts": [],
        "loadingTimeout": 90
    }
}