ReadyArt/Mistral-Small-24B-Instruct-2501_EXL2_5.0bpw_H8

Model Card for Mistral-Small-24B-Instruct-2501

Mistral Small 3 ( 2501 ) sets a new benchmark in the "small" Large Language Models category below 70B, boasting 24B parameters and achieving state-of-the-art capabilities comparable to larger models!
This model is an instruction-fine-tuned version of the base model: Mistral-Small-24B-Base-2501.

Mistral Small can be deployed locally and is exceptionally "knowledge-dense", fitting in a single RTX 4090 or a 32GB RAM MacBook once quantized.
Perfect for:

• Fast response conversational agents.
• Low latency function calling.
• Subject matter experts via fine-tuning.
• Local inference for hobbyists and organizations handling sensitive data.

For enterprises that need specialized capabilities (increased context, particular modalities, domain specific knowledge, etc.), we will be releasing commercial models beyond what Mistral AI contributes to the community.

This release demonstrates our commitment to open source, serving as a strong base model.

Learn more about Mistral Small in our blog post.

Model developper: Mistral AI Team

Key Features

• Multilingual: Supports dozens of languages, including English, French, German, Spanish, Italian, Chinese, Japanese, Korean, Portuguese, Dutch, and Polish.
• Agent-Centric: Offers best-in-class agentic capabilities with native function calling and JSON outputting.
• Advanced Reasoning: State-of-the-art conversational and reasoning capabilities.
• Apache 2.0 License: Open license allowing usage and modification for both commercial and non-commercial purposes.
• Context Window: A 32k context window.
• System Prompt: Maintains strong adherence and support for system prompts.
• Tokenizer: Utilizes a Tekken tokenizer with a 131k vocabulary size.

Benchmark results

Human evaluated benchmarks

TODO:

Publicly accesible benchmarks

Reasoning & Knowledge

Evaluation	mistral-small-24B-instruct-2501	gemma-2b-27b	llama-3.3-70b	qwen2.5-32b	gpt-4o-mini-2024-07-18
mmlu_pro_5shot_cot_instruct	0.663	0.536	0.666	0.683	0.617
gpqa_main_cot_5shot_instruct	0.453	0.344	0.531	0.404	0.377

Math & Coding

Evaluation	mistral-small-24B-instruct-2501	gemma-2b-27b	llama-3.3-70b	qwen2.5-32b	gpt-4o-mini-2024-07-18
humaneval_instruct_pass@1	0.848	0.732	0.854	0.909	0.890
math_instruct	0.706	0.535	0.743	0.819	0.761

Instruction following

Evaluation	mistral-small-24B-instruct-2501	gemma-2b-27b	llama-3.3-70b	qwen2.5-32b	gpt-4o-mini-2024-07-18
mtbench_dev	8.35	7.86	7.96	8.26	8.33
wildbench	52.27	48.21	50.04	52.73	56.13
arena_hard	0.873	0.788	0.840	0.860	0.897
ifeval	0.829	0.8065	0.8835	0.8401	0.8499

Note:

• Performance accuracy on all benchmarks were obtained through the same internal evaluation pipeline - as such, numbers may vary slightly from previously reported performance (Qwen2.5-32B-Instruct, Llama-3.3-70B-Instruct, Gemma-2-27B-IT).
• Judge based evals such as Wildbench, Arena hard and MTBench were based on gpt-4o-2024-05-13.

Basic Instruct Template (V7-Tekken)

<s>[SYSTEM_PROMPT]<system prompt>[/SYSTEM_PROMPT][INST]<user message>[/INST]<assistant response></s>[INST]<user message>[/INST]

<system_prompt>, <user message> and <assistant response> are placeholders.

Please make sure to use mistral-common as the source of truth

Usage

The model can be used with the following frameworks;

• vllm: See here
• transformers: See here

vLLM

We recommend using this model with the vLLM library to implement production-ready inference pipelines.

Note: We recommond using a relatively low temperature, such as temperature=0.15.

Installation

Make sure you install vLLM >= 0.6.4:

pip install --upgrade vllm

Also make sure you have mistral_common >= 1.5.2 installed:

pip install --upgrade mistral_common

You can also make use of a ready-to-go docker image or on the docker hub.

Server

We recommand that you use Mistral-Small-Instruct-2501 in a server/client setting.

1. Spin up a server:

vllm serve mistralai/Mistral-Small-24B-Instruct-2501 --tokenizer_mode mistral --config_format mistral --load_format mistral --enable-auto-tool-choice

Note: Running Mistral-Small-Instruct-2501 on GPU requires 60 GB of GPU RAM.

2. To ping the client you can use a simple Python snippet.

import requests
import json
from datetime import datetime, timedelta

url = "http://<your-server>:8000/v1/chat/completions"
headers = {"Content-Type": "application/json", "Authorization": "Bearer token"}

model = "mistralai/Mistral-Small-24B-Instruct-2501"

messages = [
    {
        "role": "system",
        "content": "You are a conversational agent that always answers straight to the point, always end your accurate response with an ASCII drawing of a cat."
    },
    {
        "role": "user",
        "content": "Give me 5 non-formal ways to say 'See you later' in French."
    },
]

data = {"model": model, "messages": messages}

response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.json()["choices"][0]["message"]["content"])

# Sure, here are five non-formal ways to say "See you later" in French:
#
# 1. À plus tard
# 2. À plus
# 3. Salut
# 4. À toute
# 5. Bisous
#
# ```
#  /\_/\
# ( o.o )
#  > ^ <
# ```

Offline

from vllm import LLM
from vllm.sampling_params import SamplingParams
from datetime import datetime, timedelta

SYSTEM_PROMPT = "You are a conversational agent that always answers straight to the point, always end your accurate response with an ASCII drawing of a cat."

user_prompt = "Give me 5 non-formal ways to say 'See you later' in French."

messages = [
    {
        "role": "system",
        "content": SYSTEM_PROMPT
    },
    {
        "role": "user",
        "content": user_prompt
    },
]

# note that running this model on GPU requires over 60 GB of GPU RAM
llm = LLM(model=model_name, tokenizer_mode="mistral", tensor_parallel_size=8)

sampling_params = SamplingParams(max_tokens=512, temperature=0.15)
outputs = llm.chat(messages, sampling_params=sampling_params)

print(outputs[0].outputs[0].text)
# Sure, here are five non-formal ways to say "See you later" in French:
#
# 1. À plus tard
# 2. À plus
# 3. Salut
# 4. À toute
# 5. Bisous
#
# ```
#  /\_/\
# ( o.o )
#  > ^ <
# ```

Ollama

Ollama can run this model locally on MacOS, Windows and Linux.

ollama run mistral-small

4-bit quantization (aliased to default):

ollama run mistral-small:24b-instruct-2501-q4_K_M

8-bit quantization:

ollama run mistral-small:24b-instruct-2501-q8_0

FP16:

ollama run mistral-small:24b-instruct-2501-fp16