---
language:
- en
- fr
- de
- es
- it
- pt
- zh
- ja
- ru
- ko
base_model:
- mistralai/Mistral-Small-24B-Instruct-2501
pipeline_tag: text-generation
tags:
- mistral
- mistral-small
- quantized
- W8A8
- vllm
- conversational
- text-generation-inference
- compressed-tensors
license: apache-2.0
license_name: apache-2.0
name: RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w8a8
description: This model was obtained by quantizing the weights and activations of Mistral-Small-24B-Instruct-2501 to INT8 data type.
readme: https://huggingface.co/RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w8a8/main/README.md
tasks:
- text-to-text
provider: Red Hat
license_link: https://www.apache.org/licenses/LICENSE-2.0
validated_on:
- RHOAI 2.20
- RHAIIS 3.0
- RHELAI 1.5
---
Mistral-Small-24B-Instruct-2501-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:** 03/03/2025
- **Version:** 1.0
- **Validated on:** RHOAI 2.20, RHAIIS 3.0, RHELAI 1.5
- **Model Developers:** Red Hat (Neural Magic)
### Model Optimizations
This model was obtained by quantizing activations and weights of [Mistral-Small-24B-Instruct-2501](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501) 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](https://arxiv.org/abs/2211.10438) and [GPTQ](https://arxiv.org/abs/2210.17323) algorithms is applied for quantization, as implemented in the [llm-compressor](https://github.com/vllm-project/llm-compressor) library.
## Deployment
1. Initialize vLLM server:
```
vllm serve RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w8a8 --tensor_parallel_size 1 --tokenizer_mode mistral
```
2. Send requests to the server:
```python
from openai import OpenAI
# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://:8000/v1"
client = OpenAI(
api_key=openai_api_key,
base_url=openai_api_base,
)
model = "RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w8a8"
messages = [
{"role": "user", "content": "Explain quantum mechanics clearly and concisely."},
]
outputs = client.chat.completions.create(
model=model,
messages=messages,
)
generated_text = outputs.choices[0].message.content
print(generated_text)
```
Deploy on Red Hat AI Inference Server
```bash
podman run --rm -it --device nvidia.com/gpu=all -p 8000:8000 \
--ipc=host \
--env "HUGGING_FACE_HUB_TOKEN=$HF_TOKEN" \
--env "HF_HUB_OFFLINE=0" -v ~/.cache/vllm:/home/vllm/.cache \
--name=vllm \
registry.access.redhat.com/rhaiis/rh-vllm-cuda \
vllm serve \
--tensor-parallel-size 8 \
--max-model-len 32768 \
--enforce-eager --model RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w8a8
```
See [Red Hat AI Inference Server documentation](https://docs.redhat.com/en/documentation/red_hat_ai_inference_server/) for more details.
Deploy on Red Hat Enterprise Linux AI
```bash
# Download model from Red Hat Registry via docker
# Note: This downloads the model to ~/.cache/instructlab/models unless --model-dir is specified.
ilab model download --repository docker://registry.redhat.io/rhelai1/mistral-small-24b-instruct-2501-quantized-w8a8:1.5
```
```bash
# Serve model via ilab
ilab model serve --model-path ~/.cache/instructlab/models/mistral-small-24b-instruct-2501-quantized-w8a8
# Chat with model
ilab model chat --model ~/.cache/instructlab/models/mistral-small-24b-instruct-2501-quantized-w8a8
```
See [Red Hat Enterprise Linux AI documentation](https://docs.redhat.com/en/documentation/red_hat_enterprise_linux_ai/1.4) for more details.
Deploy on Red Hat Openshift AI
```python
# Setting up vllm server with ServingRuntime
# Save as: vllm-servingruntime.yaml
apiVersion: serving.kserve.io/v1alpha1
kind: ServingRuntime
metadata:
name: vllm-cuda-runtime # OPTIONAL CHANGE: set a unique name
annotations:
openshift.io/display-name: vLLM NVIDIA GPU ServingRuntime for KServe
opendatahub.io/recommended-accelerators: '["nvidia.com/gpu"]'
labels:
opendatahub.io/dashboard: 'true'
spec:
annotations:
prometheus.io/port: '8080'
prometheus.io/path: '/metrics'
multiModel: false
supportedModelFormats:
- autoSelect: true
name: vLLM
containers:
- name: kserve-container
image: quay.io/modh/vllm:rhoai-2.20-cuda # CHANGE if needed. If AMD: quay.io/modh/vllm:rhoai-2.20-rocm
command:
- python
- -m
- vllm.entrypoints.openai.api_server
args:
- "--port=8080"
- "--model=/mnt/models"
- "--served-model-name={{.Name}}"
env:
- name: HF_HOME
value: /tmp/hf_home
ports:
- containerPort: 8080
protocol: TCP
```
```python
# Attach model to vllm server. This is an NVIDIA template
# Save as: inferenceservice.yaml
apiVersion: serving.kserve.io/v1beta1
kind: InferenceService
metadata:
annotations:
openshift.io/display-name: mistral-small-24b-instruct-2501-quantized-w8a8 # OPTIONAL CHANGE
serving.kserve.io/deploymentMode: RawDeployment
name: mistral-small-24b-instruct-2501-quantized-w8a8 # specify model name. This value will be used to invoke the model in the payload
labels:
opendatahub.io/dashboard: 'true'
spec:
predictor:
maxReplicas: 1
minReplicas: 1
model:
modelFormat:
name: vLLM
name: ''
resources:
limits:
cpu: '2' # this is model specific
memory: 8Gi # this is model specific
nvidia.com/gpu: '1' # this is accelerator specific
requests: # same comment for this block
cpu: '1'
memory: 4Gi
nvidia.com/gpu: '1'
runtime: vllm-cuda-runtime # must match the ServingRuntime name above
storageUri: oci://registry.redhat.io/rhelai1/modelcar-mistral-small-24b-instruct-2501-quantized-w8a8:1.5
tolerations:
- effect: NoSchedule
key: nvidia.com/gpu
operator: Exists
```
```bash
# make sure first to be in the project where you want to deploy the model
# oc project
# apply both resources to run model
# Apply the ServingRuntime
oc apply -f vllm-servingruntime.yaml
# Apply the InferenceService
oc apply -f qwen-inferenceservice.yaml
```
```python
# Replace and below:
# - Run `oc get inferenceservice` to find your URL if unsure.
# Call the server using curl:
curl https://-predictor-default./v1/chat/completions
-H "Content-Type: application/json" \
-d '{
"model": "mistral-small-24b-instruct-2501-quantized-w8a8",
"stream": true,
"stream_options": {
"include_usage": true
},
"max_tokens": 1,
"messages": [
{
"role": "user",
"content": "How can a bee fly when its wings are so small?"
}
]
}'
```
See [Red Hat Openshift AI documentation](https://docs.redhat.com/en/documentation/red_hat_openshift_ai/2025) 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.
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
from datasets import load_dataset
# Load model
model_stub = "mistralai/Mistral-Small-24B-Instruct-2501"
model_name = model_stub.split("/")[-1]
num_samples = 1024
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
# Data processing
def preprocess_text(example):
text = tokenizer.apply_chat_template(example["messages"], tokenize=False, add_generation_prompt=False)
return tokenizer(text, padding=False, max_length=max_seq_len, truncation=True)
ds = load_dataset("neuralmagic/calibration", name="LLM", split="train").select(range(num_samples))
ds = ds.map(preprocess_text, remove_columns=ds.column_names)
# Configure the quantization algorithm and scheme
recipe = [
SmoothQuantModifier(
smoothing_strength=0.9,
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=["lm_head"],
sequential_targets=["MistralDecoderLayer"],
dampening_frac=0.1,
targets="Linear",
scheme="W8A8",
),
]
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_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 OpenLLM Leaderboard [V1](https://huggingface.co/spaces/open-llm-leaderboard-old/open_llm_leaderboard) and [V2](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/), using the following commands:
OpenLLM Leaderboard V1:
```
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Mistral-Small-24B-Instruct-2501-FP8-Dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_config
```
OpenLLM Leaderboard V2:
```
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/Mistral-Small-24B-Instruct-2501-FP8-Dynamic",dtype=auto,add_bos_token=False,max_model_len=4096,tensor_parallel_size=1,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
--apply_chat_template \
--fewshot_as_multiturn \
--tasks leaderboard \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_config
```
### Accuracy
#### OpenLLM Leaderboard V1 evaluation scores
| Metric | mistralai/Mistral-Small-24B-Instruct-2501 | nm-testing/Mistral-Small-24B-Instruct-2501-quantized.w8a8 |
|-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
| ARC-Challenge (Acc-Norm, 25-shot) | 72.18 | 68.86 |
| GSM8K (Strict-Match, 5-shot) | 90.14 | 90.00 |
| HellaSwag (Acc-Norm, 10-shot) | 85.05 | 85.06 |
| MMLU (Acc, 5-shot) | 80.69 | 80.25 |
| TruthfulQA (MC2, 0-shot) | 65.55 | 65.69 |
| Winogrande (Acc, 5-shot) | 83.11 | 81.69 |
| **Average Score** | **79.45** | **78.59** |
| **Recovery (%)** | **100.00** | **98.92** |