InferX Catalog | Qwen3-Coder-Next-AWQ-4bit

Qwen3-Coder-Next-AWQ-4bit

This is a 4-bit AWQ quantized version of Qwen3-Coder-Next, an open-weight language model designed specifically for coding agents and local development.

cyankiwi text text2text

Log in to deploy

Metadata

Provider

cyankiwi

Modality

text

API type

text2text

Source

huggingface / cyankiwi/Qwen3-Coder-Next-AWQ-4bit

Created

2026-04-06 18:14:08 UTC

Updated

2026-04-30 15:43:45 UTC

Catalog version

4

Visibility

Published

Specifications

Parameters

80.00B

MoE

No

Max model length

128000

Image

inferx/vllm-openai:v0.19.1

Default Deploy Config

GPU count

1

vRAM

70000 MB

Summary

1xGPU 70000 MB

Recommended Use Cases

—

Model Spec

{
    "image": "inferx/vllm-openai:v0.19.1",
    "commands": [
        "--model",
        "cyankiwi/Qwen3-Coder-Next-AWQ-4bit",
        "--trust-remote-code",
        "--gpu-memory-utilization",
        "0.95",
        "--max-model-len",
        "128000",
        "--enable-auto-tool-choice",
        "--tool-call-parser",
        "qwen3_coder",
        "--tensor-parallel-size=1"
    ],
    "resources": {
        "GPU": {
            "Count": 1,
            "vRam": 70000
        }
    },
    "envs": [],
    "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
    }
}