datawhalechina--self-llm/models_mlx/configs/model_info/mlx.json

[
    {
        "Company": "Alibaba",
        "Series": "QwQ",
        "FrameworkInference": [
            "mlx"
        ],
        "Models": [
            "QwQ-0.5B-4bit"
        ]
    },
    {
        "Company": "Alibaba",
        "Series": "Qwen1.5",
        "FrameworkInference": [
            "mlx"
        ],
        "Models": [
            "Qwen1.5-0.5B-Chat-4bit",
            "Qwen1.5-1.8B-Chat-4bit",
            "Qwen1.5-MoE-A2.7B-4bit",
            "Qwen1.5-MoE-A2.7B-Chat-4bit"
        ]
    },
    {
        "Company": "Alibaba",
        "Series": "Qwen2",
        "FrameworkInference": [
            "mlx"
        ],
        "Models": [
            "Qwen2-0.5B-Instruct-4bit",
            "Qwen2-1.5B-4bit",
            "Qwen2-1.5B-Instruct-4bit"
        ]
    },
    {
        "Company": "Alibaba",
        "Series": "Qwen2-Math",
        "FrameworkInference": [
            "mlx"
        ],
        "Models": [
            "Qwen2-Math-1.5B-Instruct-4bit"
        ]
    },
    {
        "Company": "Alibaba",
        "Series": "Qwen2.5",
        "FrameworkInference": [
            "mlx"
        ],
        "Models": [
            "Qwen2.5-0.5B-4bit",
            "Qwen2.5-0.5B-Instruct-4bit",
            "Qwen2.5-1.5B-4bit",
            "Qwen2.5-1.5B-Instruct-4bit",
            "Qwen2.5-14B-Instruct-4bit",
            "Qwen2.5-32B-Instruct-4bit",
            "Qwen2.5-3B-4bit",
            "Qwen2.5-3B-Instruct-4bit",
            "Qwen2.5-7B-Instruct-4bit"
        ]
    },
    {
        "Company": "Alibaba",
        "Series": "Qwen2.5-Coder",
        "Models": [
            "Qwen2.5-Coder-0.5B-4bit",
            "Qwen2.5-Coder-0.5B-Instruct-4bit",
            "Qwen2.5-Coder-1.5B-4bit",
            "Qwen2.5-Coder-1.5B-Instruct-4bit",
            "Qwen2.5-Coder-14B-Instruct-4bit",
            "Qwen2.5-Coder-32B-Instruct-4bit",
            "Qwen2.5-Coder-3B-4bit",
            "Qwen2.5-Coder-3B-Instruct-4bit",
            "Qwen2.5-Coder-7B-Instruct-4bit"
        ]
    },
    {
        "Company": "Alibaba",
        "Series": "Qwen2.5-Math",
        "FrameworkInference": [
            "mlx"
        ],
        "Models": [
            "Qwen2.5-Math-1.5B-4bit",
            "Qwen2.5-Math-1.5B-Instruct-4bit"
        ]
    },
    {
        "Company": "Alibaba",
        "Series": "Qwen3",
        "FrameworkInference": [
            "mlx"
        ],
        "Models": [
            "Qwen3-0.6B-4bit",
            "Qwen3-0.6B-Base-4bit",
            "Qwen3-1.7B-4bit",
            "Qwen3-14B-4bit",
            "Qwen3-30B-A3B-4bit",
            "Qwen3-4B-4bit",
            "Qwen3-8B-4bit"
        ]
    },
    {
        "Company": "Alibaba",
        "Series": "Qwen3.5",
        "FrameworkInference": [
            "mlx"
        ],
        "Models": [
            "Qwen3.5-0.8B-4bit",
            "Qwen3.5-2B-4bit",
            "Qwen3.5-4B-4bit"
        ]
    },
    {
        "Company": "DeepSeek",
        "Series": "DeepSeek-R1",
        "Models": [
            "DeepSeek-R1-Distill-Llama-70B-4bit",
            "DeepSeek-R1-Distill-Llama-8B-4bit",
            "DeepSeek-R1-Distill-Qwen-1.5B-4bit",
            "DeepSeek-R1-Distill-Qwen-14B-4bit",
            "DeepSeek-R1-Distill-Qwen-32B-4bit",
            "DeepSeek-R1-Distill-Qwen-7B-4bit"
        ]
    },
    {
        "Company": "DeepSeek",
        "Series": "DeepSeek-V3",
        "Models": [
            "DeepSeek-V3-0324-4bit"
        ]
    },
    {
        "Company": "Google",
        "Series": "Gemma-2",
        "Models": [
            "gemma-2-27b-it-4bit",
            "gemma-2-2b-4bit",
            "gemma-2-2b-it-4bit",
            "gemma-2-2b-jpn-it-4bit",
            "gemma-2-9b-it-4bit",
            "gemma-2-baku-2b-it-4bit"
        ]
    },
    {
        "Company": "Google",
        "Series": "Gemma-3",
        "Models": [
            "gemma-3-12b-it-4bit",
            "gemma-3-1b-it-4bit",
            "gemma-3-1b-pt-4bit",
            "gemma-3-270m-4bit",
            "gemma-3-270m-it-4bit",
            "gemma-3-27b-it-4bit",
            "gemma-3-4b-it-4bit"
        ]
    },
    {
        "Company": "Meta",
        "Series": "Llama-3.1",
        "Models": [
            "Llama-3.1-70B-Instruct-4bit",
            "Llama-3.1-8B-Instruct-4bit"
        ]
    },
    {
        "Company": "Meta",
        "Series": "Llama-3.2",
        "Models": [
            "Llama-3.2-1B-Instruct-4bit",
            "Llama-3.2-3B-Instruct-4bit"
        ]
    },
    {
        "Company": "Meta",
        "Series": "Llama-4",
        "Models": [
            "Llama-4-Maverick-17B-128E-Instruct-4bit",
            "Llama-4-Scout-17B-16E-Instruct-4bit"
        ]
    },
    {
        "Company": "Microsoft",
        "Series": "Phi-2",
        "FrameworkInference": [
            "mlx"
        ],
        "Models": [
            "phi-2-super-4bit"
        ]
    },
    {
        "Company": "Microsoft",
        "Series": "Phi-4",
        "Models": [
            "phi-4-4bit"
        ]
    },
    {
        "Company": "Mistral",
        "Series": "Mistral",
        "Models": [
            "Ministral-3-3B-Instruct-2512-4bit",
            "Ministral-3-3B-Reasoning-2512-4bit",
            "Mistral-7B-Instruct-v0.3-4bit",
            "Mistral-Small-24B-Instruct-2501-4bit"
        ]
    },
    {
        "Company": "Moonshot",
        "Series": "Kimi",
        "FrameworkInference": [
            "mlx"
        ],
        "Models": [
            "Kimi-VL-A3B-Thinking-4bit"
        ]
    }
]