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 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

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:

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://<your-server-host>: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)

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 for more details.

# 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

# 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 for more details.

# 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

# 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

# make sure first to be in the project where you want to deploy the model
# oc project <project-name>

# apply both resources to run model

# Apply the ServingRuntime
oc apply -f vllm-servingruntime.yaml

# Apply the InferenceService
oc apply -f qwen-inferenceservice.yaml

# Replace <inference-service-name> and <cluster-ingress-domain> below:
# - Run `oc get inferenceservice` to find your URL if unsure.

# Call the server using curl:
curl https://<inference-service-name>-predictor-default.<domain>/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 for more details.

Creation

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 and V2, 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