InferX Catalog | cogito-v1-preview-qwen-14B

cogito-v1-preview-qwen-14B

Cogito-v1-preview-qwen-14B is a hybrid reasoning model developed by Deep Cogito, a San Francisco-based startup that emerged from stealth in April 2025. It is built on the Qwen 2.5 architecture but heavily modified to include self-reflection and "deep thinking" capabilities similar to OpenAI’s o1 or DeepSeek-R1.

deepcogito text text2text

Log in to deploy

Metadata

Provider

deepcogito

Modality

text

API type

text2text

Source

huggingface / deepcogito/cogito-v1-preview-qwen-14B

Created

2026-04-12 14:00:54 UTC

Updated

2026-04-20 23:14:08 UTC

Catalog version

4

Visibility

Published

Specifications

Parameters

14.00B

MoE

No

Max model length

2000

Image

inferx/vllm-openai:v0.16.0

Default Deploy Config

GPU count

1

vRAM

50000 MB

Summary

1xGPU 50000 MB

Recommended Use Cases

—

Model Spec

{
    "image": "inferx/vllm-openai:v0.16.0",
    "commands": [
        "--model",
        "deepcogito/cogito-v1-preview-qwen-14B",
        "--trust-remote-code",
        "--gpu-memory-utilization",
        "0.85",
        "--max-model-len",
        "2000"
    ],
    "resources": {
        "GPU": {
            "Count": 1,
            "vRam": 50000
        }
    },
    "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": {
            "stream": "true",
            "max_tokens": "1000",
            "temperature": "0"
        },
        "path": "v1/completions",
        "prompt": "write a quick sort algorithm.",
        "apiType": "text2text",
        "dataUrl": "",
        "prompts": [],
        "loadingTimeout": 90
    }
}