Llama-4-Scout-17B-16E-Instruct-quantized.w4a16

Model Overview

• Model Architecture: Llama4ForConditionalGeneration
  • Input: Text / Image
  • Output: Text
• Model Optimizations:
  • Activation quantization: None
  • Weight quantization: INT4
• Release Date: 04/25/2025
• 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 weights of Llama-4-Scout-17B-16E-Instruct to INT4 data type. This optimization reduces the number of bits used to represent weights from 16 to 4, reducing GPU memory requirements by approximately 75%. Weight quantization also reduces disk size requirements by approximately 75%. The llm-compressor library is used for quantization.

Deployment

This model can be deployed efficiently on vLLM, Red Hat Enterprise Linux AI, and Openshift AI, as shown in the example below.

Deploy on vLLM

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16"
number_gpus = 4

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

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

outputs = llm.generate(prompt, sampling_params)

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

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

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/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16

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/llama-4-scout-17b-16e-instruct-quantized-w4a16:1.5

# Serve model via ilab
ilab model serve --model-path ~/.cache/instructlab/models/llama-4-scout-17b-16e-instruct-quantized-w4a16
  
# Chat with model
ilab model chat --model ~/.cache/instructlab/models/llama-4-scout-17b-16e-instruct-quantized-w4a16

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: Llama-4-Scout-17B-16E-Instruct-quantized.w4a16 # OPTIONAL CHANGE
    serving.kserve.io/deploymentMode: RawDeployment
  name: Llama-4-Scout-17B-16E-Instruct-quantized.w4a16          # 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-llama-4-scout-17b-16e-instruct-quantized-w4a16:1.5
    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": "Llama-4-Scout-17B-16E-Instruct-quantized.w4a16",
    "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.

Evaluation

The model was evaluated on the OpenLLM leaderboard tasks (v1 and v2), long context RULER, multimodal MMMU, and multimodal ChartQA. All evaluations are obtained through lm-evaluation-harness.

OpenLLM v1

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=8,gpu_memory_utilization=0.7,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks openllm \
  --batch_size auto 

OpenLLM v2

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16",dtype=auto,add_bos_token=False,max_model_len=16384,tensor_parallel_size=8,gpu_memory_utilization=0.5,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks leaderboard \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --batch_size auto 

Long Context RULER

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16",dtype=auto,add_bos_token=False,max_model_len=524288,tensor_parallel_size=8,gpu_memory_utilization=0.9,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks ruler \
  --metadata='{"max_seq_lengths":[131072]}' \
  --batch_size auto 

Multimodal MMMU

lm_eval \
  --model vllm-vlm \
  --model_args pretrained="RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16",dtype=auto,add_bos_token=False,max_model_len=1000000,tensor_parallel_size=8,gpu_memory_utilization=0.9,enable_chunked_prefill=True,trust_remote_code=True,max_images=10 \
  --tasks mmmu_val \
  --apply_chat_template \
  --batch_size auto 

Multimodal ChartQA

export VLLM_MM_INPUT_CACHE_GIB=8
lm_eval \
  --model vllm-vlm \
  --model_args pretrained="RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16",dtype=auto,add_bos_token=False,max_model_len=1000000,tensor_parallel_size=8,gpu_memory_utilization=0.9,enable_chunked_prefill=True,trust_remote_code=True,max_images=10 \
  --tasks chartqa \
  --apply_chat_template \
  --batch_size auto 

Accuracy