InferX Catalog | DeepSeek-Coder-V2-Lite-Instruct

DeepSeek-Coder-V2-Lite-Instruct

A lightweight coding model designed for efficient code generation and reasoning.

Qwen text text2text reasoning coding

Log in to deploy

deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct is an instruction-tuned coding model from the DeepSeek-Coder V2 family, optimized for code generation, debugging, and reasoning across multiple programming languages, while maintaining efficient performance for cost-effective deployments and developer tools.

Metadata

Provider

Qwen

Modality

text

API type

text2text

Source

huggingface / deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct

Created

2026-04-06 05:34:45 UTC

Updated

2026-04-13 02:57:13 UTC

Catalog version

2

Visibility

Published

Specifications

Parameters

16.00B

MoE

No

Max model length

32768

Image

vllm/vllm-openai:v0.16.0

Default Deploy Config

GPU count

1

vRAM

40000 MB

Summary

1xGPU 40000 MB

Recommended Use Cases

—

Model Spec

{
    "image": "vllm/vllm-openai:v0.16.0",
    "commands": [
        "--model",
        "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct",
        "--trust-remote-code",
        "--gpu-memory-utilization",
        "0.95",
        "--max-model-len",
        "32768",
        "--tensor-parallel-size=1"
    ],
    "resources": {
        "GPU": {
            "Count": 1,
            "vRam": 40000
        }
    },
    "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
    }
}