Mistral Small 3.1 24B Instruct 2503 Quantized.w8a8

Developed by RedHatAI

This is an INT8-quantized Mistral-Small-3.1-24B-Instruct-2503 model, optimized by Red Hat and Neural Magic, suitable for fast response and low-latency scenarios.

Safetensors

Supports Multiple LanguagesOpen Source License:Apache-2.0 #INT8 quantization #Multimodal understanding #Low-latency inference

Downloads 833

Release Time : 4/15/2025

Model Overview

This model is a quantized version of Mistral-Small-3.1-24B-Instruct-2503, significantly reducing GPU memory requirements and improving computational efficiency by quantizing weights and activations to INT8.

Model Features

Efficient Quantization

Reduces GPU memory requirements by approximately 50% and increases computational throughput by about 2x through INT8 quantization technology

Multilingual Support

Supports text generation and understanding in 24 languages

Versatile Applications

Suitable for various tasks such as dialogue agents, function calling, document understanding, and visual understanding

Fast Response

The optimized model is particularly suitable for applications requiring low latency

Model Capabilities

Text generation

Multilingual processing

Dialogue agents

Function calling

Long-document understanding

Visual understanding

Programming and mathematical reasoning

Use Cases

Dialogue Systems

Customer Service Chatbot

Deploy fast-response customer service agents

Reduces response latency and improves user experience

Development Tools

Code Assistance

Helps developers with programming and debugging

Improves development efficiency

Content Understanding

Long-Document Summarization

Quickly understands and summarizes long documents

Enhances information processing efficiency

language:

en
fr
de
es
pt
it
ja
ko
ru
zh
ar
fa
id
ms
ne
pl
ro
sr
sv
tr
uk
vi
hi
bn license: apache-2.0 library_name: vllm base_model:
mistralai/Mistral-Small-3.1-24B-Instruct-2503 pipeline_tag: image-text-to-text tags:
neuralmagic
redhat
llmcompressor
quantized
int8

Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8

Model Overview

Model Architecture: Mistral3ForConditionalGeneration
- Input: Text / Image
- Output: Text
Model Optimizations:
- Activation quantization: INT8
- Weight quantization: INT8
Intended Use Cases: It is ideal for:
- Fast-response conversational agents.
- Low-latency function calling.
- Subject matter experts via fine-tuning.
- Local inference for hobbyists and organizations handling sensitive data.
- Programming and math reasoning.
- Long document understanding.
- Visual understanding.
Out-of-scope: Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages not officially supported by the model.
Release Date: 04/15/2025
Version: 1.0
Model Developers: Red Hat (Neural Magic)

Model Optimizations

This model was obtained by quantizing activations and weights of Mistral-Small-3.1-24B-Instruct-2503 to INT8 data type. This optimization reduces the number of bits used to represent weights and activations from 16 to 8, reducing GPU memory requirements (by approximately 50%) and increasing matrix-multiply compute throughput (by approximately 2x). Weight quantization also reduces disk size requirements by approximately 50%.

Only weights and activations of the linear operators within transformers blocks are quantized. Weights are quantized with a symmetric static per-channel scheme, whereas activations are quantized with a symmetric dynamic per-token scheme. A combination of the SmoothQuant and GPTQ algorithms is applied for quantization, as implemented in the llm-compressor library.

Deployment

This model can be deployed efficiently using the vLLM backend, as shown in the example below.

from vllm import LLM, SamplingParams
from transformers import AutoProcessor

model_id = "RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic"
number_gpus = 1

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)
processor = AutoProcessor.from_pretrained(model_id)

messages = [{"role": "user", "content": "Give me a short introduction to large language model."}]

prompts = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

llm = LLM(model=model_id, tensor_parallel_size=number_gpus)

outputs = llm.generate(prompts, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)

vLLM aslo supports OpenAI-compatible serving. See the documentation for more details.

Creation

Creation details

This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below.

from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableMistral3ForConditionalGeneration
from datasets import load_dataset, interleave_datasets
from PIL import Image
import io

# Load model
model_stub = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
model_name = model_stub.split("/")[-1]

num_text_samples = 1024
num_vision_samples = 1024
max_seq_len = 8192

processor = AutoProcessor.from_pretrained(model_stub)

model = TraceableMistral3ForConditionalGeneration.from_pretrained(
    model_stub,
    device_map="auto",
    torch_dtype="auto",
)

# Text-only data subset
def preprocess_text(example):
    input = {
        "text": processor.apply_chat_template(
            example["messages"],
            add_generation_prompt=False,
        ),
        "images": None,
    }
    tokenized_input = processor(**input, max_length=max_seq_len, truncation=True)
    tokenized_input["pixel_values"] = tokenized_input.get("pixel_values", None)
    tokenized_input["image_sizes"] = tokenized_input.get("image_sizes", None)
    return tokenized_input

dst = load_dataset("neuralmagic/calibration", name="LLM", split="train").select(range(num_text_samples))
dst = dst.map(preprocess_text, remove_columns=dst.column_names)

# Text + vision data subset
def preprocess_vision(example):
    messages = []
    image = None
    for message in example["messages"]:
        message_content = []
        for content in message["content"]:
            if content["type"] == "text":
                message_content.append({"type": "text", "text": content["text"]})
            else:
                message_content.append({"type": "image"})
                image = Image.open(io.BytesIO(content["image"]))

        messages.append(
            {
                "role": message["role"],
                "content": message_content,
            }
        )

    input = {
        "text": processor.apply_chat_template(
            messages,
            add_generation_prompt=False,
        ),
        "images": image,
    }
    tokenized_input = processor(**input, max_length=max_seq_len, truncation=True)
    tokenized_input["pixel_values"] = tokenized_input.get("pixel_values", None)
    tokenized_input["image_sizes"] = tokenized_input.get("image_sizes", None)
    return tokenized_input

dsv = load_dataset("neuralmagic/calibration", name="VLM", split="train").select(range(num_vision_samples))
dsv = dsv.map(preprocess_vision, remove_columns=dsv.column_names)

# Interleave subsets
ds = interleave_datasets((dsv, dst))

# Configure the quantization algorithm and scheme
recipe = [
    SmoothQuantModifier(
      smoothing_strength=0.8,
      mappings=[
          [["re:.*q_proj", "re:.*k_proj", "re:.*v_proj"], "re:.*input_layernorm"],
          [["re:.*gate_proj", "re:.*up_proj"], "re:.*post_attention_layernorm"],
          [["re:.*down_proj"], "re:.*up_proj"],
      ],
    ),
    GPTQModifier(
        ignore=["language_model.lm_head", "re:vision_tower.*", "re:multi_modal_projector.*"],
        sequential_targets=["MistralDecoderLayer"],
        dampening_frac=0.01,
        targets="Linear",
        scheme="W8A8",
    ),
]

# Define data collator
def data_collator(batch):
    import torch
    assert len(batch) == 1
    collated = {}
    for k, v in batch[0].items():
        if v is None:
            continue
        if k == "input_ids":
            collated[k] = torch.LongTensor(v)
        elif k == "pixel_values":
            collated[k] = torch.tensor(v, dtype=torch.bfloat16)
        else:
            collated[k] = torch.tensor(v)
    return collated


# Apply quantization
oneshot(
    model=model,
    dataset=ds, 
    recipe=recipe,
    max_seq_length=max_seq_len,
    data_collator=data_collator,
    num_calibration_samples=num_text_samples + num_vision_samples,
)

# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w8a8"
model.save_pretrained(save_path)
processor.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")

Evaluation

The model was evaluated on the OpenLLM leaderboard tasks (version 1), MMLU-pro, GPQA, HumanEval and MBPP. Non-coding tasks were evaluated with lm-evaluation-harness, whereas coding tasks were evaluated with a fork of evalplus. vLLM is used as the engine in all cases.

Evaluation details

MMLU

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks mmlu \
  --num_fewshot 5 \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

ARC Challenge

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks arc_challenge \
  --num_fewshot 25 \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

GSM8k

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.9,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks gsm8k \
  --num_fewshot 8 \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

Hellaswag

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks hellaswag \
  --num_fewshot 10 \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

Winogrande

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks winogrande \
  --num_fewshot 5 \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

TruthfulQA

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks truthfulqa \
  --num_fewshot 0 \
  --apply_chat_template\
  --batch_size auto

MMLU-pro

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks mmlu_pro \
  --num_fewshot 5 \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

MMMU

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.9,max_images=8,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks mmmu \
  --apply_chat_template\
  --batch_size auto

ChartQA

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.9,max_images=8,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks chartqa \
  --apply_chat_template\
  --batch_size auto

Coding

The commands below can be used for mbpp by simply replacing the dataset name.

Generation

python3 codegen/generate.py \
  --model RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8 \
  --bs 16 \
  --temperature 0.2 \
  --n_samples 50 \
  --root "." \
  --dataset humaneval

Sanitization

python3 evalplus/sanitize.py \
  humaneval/RedHatAI--Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8_vllm_temp_0.2

Evaluation

evalplus.evaluate \
  --dataset humaneval \
  --samples humaneval/RedHatAI--Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8_vllm_temp_0.2-sanitized

Accuracy

Category	Benchmark	Mistral-Small-3.1-24B-Instruct-2503	Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8 (this model)	Recovery
OpenLLM v1	MMLU (5-shot)	80.67	80.40	99.7%
	ARC Challenge (25-shot)	72.78	73.46	100.9%
	GSM-8K (5-shot, strict-match)	56.68	61.18	104.3%
	Hellaswag (10-shot)	83.70	82.26	98.3%
	Winogrande (5-shot)	83.74	80.90	96.6%
	TruthfulQA (0-shot, mc2)	70.62	69.15	97.9%
	Average	75.03	74.56	99.4%
	MMLU-Pro (5-shot)	67.25	66.54	98.9%
	GPQA CoT main (5-shot)	42.63	44.64	104.7%
	GPQA CoT diamond (5-shot)	45.96	41.92	91.2%
Coding	HumanEval pass@1	84.70	84.20	99.4%
	HumanEval+ pass@1	79.50	81.00	101.9%
	MBPP pass@1	71.10	72.10	101.4%
	MBPP+ pass@1	60.60	62.10	100.7%
Vision	MMMU (0-shot)	52.11	53.11	101.9%
Vision	ChartQA (0-shot)	81.36	82.36	101.2%

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご