InferX Catalog | Qwen3.5-2B

Qwen3.5-2B

Qwen3.5-2B

Qwen text text2text

Log in to deploy

Metadata

Provider

Qwen

Modality

text

API type

text2text

Source

huggingface / Qwen/Qwen3.5-2B

Created

2026-06-21 13:01:39 UTC

Updated

2026-06-21 13:01:40 UTC

Catalog version

1

Visibility

Published

Specifications

Parameters

—

MoE

No

Max model length

—

Image

vllm/vllm-openai:v0.19.0

Default Deploy Config

GPU count

1

vRAM

70000 MB

Summary

1xGPU 70000 MB

Recommended Use Cases

—

Model Spec

{
    "image": "vllm/vllm-openai:v0.19.0",
    "commands": [
        "--model",
        "Qwen/Qwen3.5-4B",
        "--trust-remote-code",
        "--gpu-memory-utilization",
        "0.95",
        "--enable-auto-tool-choice",
        "--tool-call-parser",
        "qwen3_coder",
        "--uvicorn-log-level",
        "warning",
        "--max-num-batched-tokens",
        "262000",
        "--max-num-batched-tokens",
        "12288",
        "--default-chat-template-kwargs",
        "{\"enable_thinking\": false}",
        "--enable-prefix-caching",
        "--enable-chunked-prefill",
        "--tensor-parallel-size",
        "1"
    ],
    "resources": {
        "GPU": {
            "Count": 1,
            "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": {
            "model": "Qwen/Qwen3.5-4B",
            "stream": "true",
            "max_tokens": "1000",
            "temperature": "0"
        },
        "path": "v1/completions",
        "prompt": "write a quick sort algorithm.",
        "apiType": "text2text",
        "dataUrl": "",
        "prompts": [],
        "raw_query": false,
        "max_tokens": 0,
        "loadingTimeout": 90
    }
}