InferX Catalog | notux-8x7b-v1-AWQ

notux-8x7b-v1-AWQ

Notux-8x7b-v1-AWQ is a high-performance, 4-bit quantized version of the Notux-8x7b-v1 model. It combines a state-of-the-art Mixture-of-Experts (MoE) architecture with Activation-aware Weight Quantization (AWQ) for efficient deployment on NVIDIA GPUs.

TheBloke text text2text

Log in to deploy

Metadata

Provider

TheBloke

Modality

text

API type

text2text

Source

huggingface / TheBloke/notux-8x7b-v1-AWQ

Created

2026-04-12 18:29:35 UTC

Updated

2026-04-13 03:14:28 UTC

Catalog version

2

Visibility

Published

Specifications

Parameters

56.00B

MoE

No

Max model length

2000

Image

vllm/vllm-openai:v0.16.0

Default Deploy Config

GPU count

1

vRAM

52000 MB

Summary

1xGPU 52000 MB

Recommended Use Cases

—

Model Spec

{
    "image": "vllm/vllm-openai:v0.16.0",
    "commands": [
        "--model",
        "TheBloke/notux-8x7b-v1-AWQ",
        "--trust-remote-code",
        "--gpu-memory-utilization",
        "0.95",
        "--max-model-len",
        "2000"
    ],
    "resources": {
        "GPU": {
            "Count": 1,
            "vRam": 52000
        }
    },
    "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
    }
}