InferX | Serverless Inference Platform

Model Huihui-Qwen3-Next-80B-A3B-Thinking-abliterated

Namespace	Model Name	Type	Standby GPU	Standby Pageable	Standby Pinned Memory	GPU Count	vRam (MB)	CPU	Memory (MB)	State	Revision
Trial	Huihui-Qwen3-Next-80B-A3B-Thinking-abliterated	text2text	File	File	File	4	45000	12.0	100000	Normal	85

Prompt

Sample Rest Call

Pods

Tenant	Namespace	Pod Name	State	Required Resource	Allocated Resource	GPU
public	Trial	public/Trial/Huihui-Qwen3-Next-80B-A3B-Thinking-abliterated/85/140	Standby	CPU 12000 Mem 100000 CacheMem 0 GPU Type Any GPU Count 4 GPU vRam 45000 GPU Contexts 0	Node Name g8398d4 CPU 0 Memory 0 Cache Memory 0	GPU Type NVIDIA H100 80GB HBM3 vRam 0 Slot Size 268435456 Total Slot Count 285 Max Context Per GPU 1

Logs

tenant	namespace	model name	revision	id	node name	create time	exit info	state
public	Trial	Huihui-Qwen3-Next-80B-A3B-Thinking-abliterated	85	88	g8398d4	2026-03-01 22:54:52	None	log

Snapshot History

tenant	namespace	model name	revision	nodename	state	detail	updatetime
public	Trial	Huihui-Qwen3-Next-80B-A3B-Thinking-abliterated	85	g8398d4	Scheduled	Scheduled	2026-03-01 22:40:08
public	Trial	Huihui-Qwen3-Next-80B-A3B-Thinking-abliterated	85	g8398d4	Done	Done	2026-03-01 22:54:52

Model Spec

{
    "image": "vllm/vllm-openai:v0.15.0",
    "commands": [
        "--model",
        "huihui-ai/Huihui-Qwen3-Next-80B-A3B-Thinking-abliterated",
        "--disable-custom-all-reduce",
        "--trust-remote-code",
        "--gpu-memory-utilization",
        "0.99",
        "--max-model-len",
        "32768",
        "--tensor-parallel-size=4"
    ],
    "resources": {
        "GPU": {
            "Count": 4,
            "vRam": 45000
        }
    },
    "envs": [],
    "sample_query": {
        "apiType": "text2text",
        "path": "v1/completions",
        "prompt": "write a quick sort algorithm.",
        "prompts": [],
        "dataUrl": "",
        "body": {
            "max_tokens": "200",
            "model": "huihui-ai/Huihui-Qwen3-Next-80B-A3B-Thinking-abliterated",
            "stream": "true",
            "temperature": "0"
        },
        "loadingTimeout": 90
    },
    "policy": {
        "Obj": {
            "queue_timeout": 30.0,
            "scalein_timeout": 1.0
        }
    }
}

InferX — Serverless GPU Inference Platform for Production Workloads