InferX Catalog | Mixtral-8x7B-Instruct-v0.1

Mixtral-8x7B-Instruct-v0.1

Mixtral-8x7B-Instruct-v0.1 is a high-performance Sparse Mixture-of-Experts (SMoE) model released by Mistral AI.

mistralai text text2text

Log in to deploy

Metadata

Provider

mistralai

Modality

text

API type

text2text

Source

huggingface / mistralai/Mixtral-8x7B-Instruct-v0.1

Created

2026-04-07 16:43:08 UTC

Updated

2026-04-13 23:37:23 UTC

Catalog version

4

Visibility

Published

Specifications

Parameters

56.00B

MoE

No

Max model length

2000

Image

vllm/vllm-openai:v0.15.0

Default Deploy Config

GPU count

2

vRAM

70000 MB

Summary

2xGPU 70000 MB

Recommended Use Cases

—

Model Spec

{
    "image": "vllm/vllm-openai:v0.15.0",
    "commands": [
        "--model",
        "mistralai/Mixtral-8x7B-Instruct-v0.1",
        "--trust-remote-code",
        "--max-model-len",
        "2000",
        "--tensor-parallel-size=2"
    ],
    "resources": {
        "GPU": {
            "Count": 2,
            "vRam": 70000
        }
    },
    "envs": [
        [
            "VLLM_ALLREDUCE_USE_SYMM_MEM",
            "0"
        ]
    ],
    "sample_query": {
        "body": {
            "stream": "true",
            "max_tokens": "1000",
            "temperature": "0"
        },
        "path": "v1/completions",
        "prompt": "Find the value of $x$ that satisfies the equation $4x+5 = 6x+7$.",
        "apiType": "text2text",
        "dataUrl": "",
        "prompts": [],
        "loadingTimeout": 90
    }
}