AI Models
    MIST Mini 8B Thinking

    OlaverseMIST Mini 8B Thinking

    MIST family · open weights on Hugging Face.

    Reasoning-tuned MIST model trained with GRPO to think step-by-step before answering.

    Transformers
    Safetensors
    Llama
    Text Generation
    Reasoning
    Grpo
    Thinking
    Llama 3.1
    Mist
    Conversational
    English
    Base: olaverse/MIST-Mini-8B
    Base: olaverse/MIST-Mini-8B
    Licence: llama3.1
    Text Generation Inference
    Endpoints Compatible
    3
    Likes
    291
    Downloads
    May 2026
    Created

    Model Card

    Built for production use.

    Open-weights repository on Hugging Face

    Integrated ecosystem protocol tier.

    Compatible with Transformers library

    Integrated ecosystem protocol tier.

    Optimised for low-latency inference

    Integrated ecosystem protocol tier.

    Community engagement: 3 likes

    Integrated ecosystem protocol tier.

    Quick Start

    Use MIST Mini 8B Thinking, straight from its model card.

    example.py
    from the model card
    from transformers import AutoModelForCausalLM, AutoTokenizer
    model = AutoModelForCausalLM.from_pretrained(
    "olaverse/MIST-Mini-8B-Thinking",
    torch_dtype="auto",
    device_map="auto",
    )
    tokenizer = AutoTokenizer.from_pretrained("olaverse/MIST-Mini-8B-Thinking")
    messages = [
    {
    "role": "system",
    "content": "Think step by step inside <think> tags before answering."
    },
    {
    "role": "user",
    "content": "If a train travels 120 miles in 2 hours, what is its speed?"
    }
    ]
    text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
    )
    inputs = tokenizer(text, return_tensors="pt").to("cuda")
    outputs = model.generate(**inputs, max_new_tokens=1024, temperature=0.7, do_sample=True)
    print(tokenizer.decode(outputs[0], skip_special_tokens=True))
    Model Card

    Official Repository README

    Dynamically loaded from Hugging Face

    Model card metadata is available on Hugging Face.

    Built with

    Transformers PyTorch Python
    Built by Olaverse Labs

    Ready to try MIST Mini 8B Thinking?

    Reasoning-tuned MIST model trained with GRPO to think step-by-step before answering.

    Model Ecosystem

    Explore More Models