InferX Catalog | Qwen3-Coder-Next-FP8

Qwen3-Coder-Next-FP8

Qwen3-Coder-Next-FP8, an open-weight language model designed specifically for coding agents and local development.

Qwen text text2text

Log in to deploy

Metadata

Provider

Qwen

Modality

text

API type

text2text

Source

huggingface / Qwen/Qwen3-Coder-Next-FP8

Created

2026-04-06 18:49:10 UTC

Updated

2026-04-30 22:06:10 UTC

Catalog version

7

Visibility

Published

Specifications

Parameters

80.00B

MoE

No

Max model length

248000

Image

inferx/vllm-openai:v0.19.1

Default Deploy Config

GPU count

2

vRAM

66000 MB

Summary

2xGPU 66000 MB

Recommended Use Cases

—

Model Spec

{
    "image": "inferx/vllm-openai:v0.19.1",
    "commands": [
        "--model",
        "Qwen/Qwen3-Coder-Next-FP8",
        "--trust-remote-code",
        "--gpu-memory-utilization",
        "0.95",
        "--max-model-len",
        "248000",
        "--enable-auto-tool-choice",
        "--tool-call-parser",
        "qwen3_coder",
        "--tensor-parallel-size=2"
    ],
    "resources": {
        "GPU": {
            "Count": 2,
            "vRam": 66000
        }
    },
    "envs": [
        [
            "VLLM_USE_DEEP_GEMM",
            "0"
        ],
        [
            "VLLM_ALLREDUCE_USE_SYMM_MEM",
            "0"
        ]
    ],
    "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
    }
}