Instructions to use RedHatAI/Qwen3.5-9B-FP8-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Qwen3.5-9B-FP8-dynamic with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="RedHatAI/Qwen3.5-9B-FP8-dynamic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("RedHatAI/Qwen3.5-9B-FP8-dynamic")
model = AutoModelForImageTextToText.from_pretrained("RedHatAI/Qwen3.5-9B-FP8-dynamic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RedHatAI/Qwen3.5-9B-FP8-dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Qwen3.5-9B-FP8-dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen3.5-9B-FP8-dynamic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Qwen3.5-9B-FP8-dynamic

SGLang

How to use RedHatAI/Qwen3.5-9B-FP8-dynamic with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RedHatAI/Qwen3.5-9B-FP8-dynamic" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen3.5-9B-FP8-dynamic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RedHatAI/Qwen3.5-9B-FP8-dynamic" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen3.5-9B-FP8-dynamic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Qwen3.5-9B-FP8-dynamic with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Qwen3.5-9B-FP8-dynamic
```

Qwen3.5-9B-FP8-dynamic

Model Overview

Model Architecture: Qwen/Qwen3.5-9B
- Input: Text / Image
- Output: Text
Model Optimizations:
- Weight quantization: FP8
- Activation quantization: FP8
- Model size: 14.0 GB (reduced from 19.3 GB in BF16)
Release Date: 2026-05-11
Version: 1.0
Model Developers: RedHatAI

This model is a quantized version of Qwen/Qwen3.5-9B. Evaluation results and reproduction steps are provided below.

Model Optimizations

This model was obtained by quantizing the weights and activations of Qwen/Qwen3.5-9B to FP8 data type, ready for inference with vLLM.

This optimization reduces the model weights from 19.3 GB to 14.0 GB on disk (~27% reduction). Activations are quantized dynamically at inference time using per-tensor scaling, requiring no calibration data.

Only the weights and activations of the linear operators within transformer blocks are quantized using LLM Compressor.

Deployment

Use with vLLM

Initialize vLLM server:

Multimodal (vision + text):

vllm serve RedHatAI/Qwen3.5-9B-FP8-dynamic \
  --reasoning-parser qwen3 \
  --max-model-len 262144

Text-only (lower memory):

vllm serve RedHatAI/Qwen3.5-9B-FP8-dynamic \
  --reasoning-parser qwen3 \
  --max-model-len 262144 \
  --language-model-only

Send requests to the server:

from openai import OpenAI

openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

model = "RedHatAI/Qwen3.5-9B-FP8-dynamic"

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)

Creation

This model was created by applying LLM Compressor using data-free FP8 dynamic quantization, as presented in the code snippet below.

from compressed_tensors.utils import save_mtp_tensors_to_checkpoint
from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier
from transformers import AutoProcessor, AutoTokenizer, Qwen3_5ForConditionalGeneration

MODEL_ID = "Qwen/Qwen3.5-9B"

IGNORE_LAYERS = [
    "re:.*lm_head",
    "re:.*embed_tokens$",
    "re:.*visual.*",
    "re:.*model.visual.*",
    "re:.*linear_attn.*",
]

model = Qwen3_5ForConditionalGeneration.from_pretrained(MODEL_ID, dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
processor = AutoProcessor.from_pretrained(MODEL_ID)

recipe = QuantizationModifier(
    targets="Linear",
    scheme="FP8_DYNAMIC",
    ignore=IGNORE_LAYERS,
)

oneshot(model=model, recipe=recipe)

model.save_pretrained("Qwen3.5-9B-FP8-dynamic", save_compressed=True)
processor.save_pretrained("Qwen3.5-9B-FP8-dynamic")
save_mtp_tensors_to_checkpoint(source_model=MODEL_ID, dest_dir="Qwen3.5-9B-FP8-dynamic")

Package versions

llm-compressor==0.10.1.dev44+g437f8afe
compressed-tensors==0.14.1a20260325
transformers==5.3.0
vllm==0.18.1
lm-eval — neuralmagic/lm-evaluation-harness@741f1d8 (branch: mmlu-pro-chat-variant)
lighteval — neuralmagic/lighteval@6f0f351 (branch: eldar-fix-litellm)

Evaluation

This model was evaluated on GSM8k-Platinum, MMLU-Pro, IFEval, Math 500, AIME 2025, and GPQA Diamond using lm-evaluation-harness and lighteval, with inference served via vLLM.

Accuracy

Category	Benchmark	Qwen/Qwen3.5-9B	RedHatAI/Qwen3.5-9B-FP8-dynamic	Recovery
Instruction Following	GSM8k-Platinum (0-shot)	94.7%	94.5%	99.8%
	MMLU-Pro (0-shot)	82.5%	82.4%	99.9%
	IFEval — prompt strict (0-shot)	90.3%	88.9%	98.4%
	IFEval — instruction strict (0-shot)	92.9%	92.0%	99.0%
Reasoning	Math 500 (0-shot)	85.0%	84.7%	99.7%
	AIME 2025 (0-shot)	88.3%	87.9%	99.5%
	GPQA Diamond (0-shot)	84.0%	83.8%	99.8%

Reproduction

The results were obtained using the following commands. GSM8k-Platinum, MMLU-Pro, IFEval, Math 500, and GPQA Diamond were each run 3 times with different seeds and results averaged. AIME 2025 was run 8 times. The vLLM server was started with --language-model-only for all evaluations.

GSM8k-Platinum (lm-eval, 0-shot, 3 repetitions)

lm_eval --model local-chat-completions \
  --tasks gsm8k_platinum_cot_llama \
  --model_args "model=RedHatAI/Qwen3.5-9B-FP8-dynamic,max_length=96000,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=100,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=3600" \
  --num_fewshot 0 \
  --apply_chat_template \
  --output_path results_gsm8k_platinum.json \
  --seed <SEED> \
  --gen_kwargs "do_sample=True,temperature=1.0,top_p=0.95,top_k=20,min_p=0.0,presence_penalty=1.5,repetition_penalty=1.0,max_gen_toks=65536,seed=<SEED>"

Seeds used: 42, 1234, 4158

MMLU-Pro (lm-eval, 0-shot, 3 repetitions)

lm_eval --model local-chat-completions \
  --tasks mmlu_pro_chat \
  --model_args "model=RedHatAI/Qwen3.5-9B-FP8-dynamic,max_length=96000,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=100,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=3600" \
  --num_fewshot 0 \
  --apply_chat_template \
  --output_path results_mmlu_pro.json \
  --seed <SEED> \
  --gen_kwargs "do_sample=True,temperature=1.0,top_p=0.95,top_k=20,min_p=0.0,presence_penalty=1.5,repetition_penalty=1.0,max_gen_toks=65536,seed=<SEED>"

Seeds used: 42, 1234, 4158

IFEval (lm-eval, 0-shot, 3 repetitions)

lm_eval --model local-chat-completions \
  --tasks ifeval \
  --model_args "model=RedHatAI/Qwen3.5-9B-FP8-dynamic,max_length=96000,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=100,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=3600" \
  --num_fewshot 0 \
  --apply_chat_template \
  --output_path results_ifeval.json \
  --seed <SEED> \
  --gen_kwargs "do_sample=True,temperature=1.0,top_p=0.95,top_k=20,min_p=0.0,presence_penalty=1.5,repetition_penalty=1.0,max_gen_toks=65536,seed=<SEED>"

Seeds used: 42, 1234, 4158

Math 500 (lighteval, 0-shot, 3 repetitions)

lighteval endpoint litellm \
  "model_name=hosted_vllm/RedHatAI/Qwen3.5-9B-FP8-dynamic,provider=hosted_vllm,base_url=http://0.0.0.0:8000/v1,timeout=3600,concurrent_requests=100,generation_parameters={temperature:1.0,max_new_tokens:65536,top_p:0.95,top_k:20,min_p:0.0,presence_penalty:1.5,repetition_penalty:1.0,seed:<SEED>}" \
  "math_500@k=1@n=1|0" \
  --output-dir results_math500 \
  --save-details

Seeds used: 42, 1234, 4158

AIME 2025 (lighteval, 0-shot, 8 repetitions)

lighteval endpoint litellm \
  "model_name=hosted_vllm/RedHatAI/Qwen3.5-9B-FP8-dynamic,provider=hosted_vllm,base_url=http://0.0.0.0:8000/v1,timeout=3600,concurrent_requests=100,generation_parameters={temperature:1.0,max_new_tokens:65536,top_p:0.95,top_k:20,min_p:0.0,presence_penalty:1.5,repetition_penalty:1.0,seed:<SEED>}" \
  "aime25@k=1@n=1|0" \
  --output-dir results_aime25 \
  --save-details

Seeds used: 42, 1234, 1356, 3344, 4158, 5322, 5678, 9843

GPQA Diamond (lighteval, 0-shot, 3 repetitions)

lighteval endpoint litellm \
  "model_name=hosted_vllm/RedHatAI/Qwen3.5-9B-FP8-dynamic,provider=hosted_vllm,base_url=http://0.0.0.0:8000/v1,timeout=3600,concurrent_requests=100,generation_parameters={temperature:1.0,max_new_tokens:65536,top_p:0.95,top_k:20,min_p:0.0,presence_penalty:1.5,repetition_penalty:1.0,seed:<SEED>}" \
  "gpqa:diamond@k=1@n=1|0" \
  --output-dir results_gpqa_diamond \
  --save-details

Seeds used: 42, 1234, 4158

Downloads last month: -

Safetensors

Model size

9B params

Tensor type

BF16

F8_E4M3

Model tree for RedHatAI/Qwen3.5-9B-FP8-dynamic

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(204)

this model