Qwen3-VL-235B-A22B-Instruct-NVFP4 👁 Model Icon

👁 Validated Badge

Model Overview

• Model Architecture: Qwen/Qwen3-VL-235B-A22B-Instruct
  • Input: Text
  • Output: Text
• Model Optimizations:
  • Weight quantization: FP4
  • Activation quantization: FP4
• Out-of-scope: Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English.
• Release Date: 10/29/2025
• Version: 1.0
• Model Developers: RedHatAI
• ModelCar Storage URI: oci://registry.redhat.io/rhai/modelcar-qwen3-vl-235b-a22b-instruct-nvfp4:3.0
• Validated on vLLM: 0.13.0
• Validated on RHAIIS: 3.3
• Validated on RHOAI: 3.3

This model is a quantized version of Qwen/Qwen3-VL-235B-A22B-Instruct. It was evaluated on a several tasks to assess the its quality in comparison to the unquatized model.

Model Optimizations

This model was obtained by quantizing the weights and activations of Qwen/Qwen3-VL-235B-A22B-Instruct to FP4 data type, ready for inference with vLLM>=0.9.1 This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%.

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

Deployment

Use with vLLM

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

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4"
number_gpus = 1

sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [
 {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
 {"role": "user", "content": "Who are you?"},
]

prompts = tokenizer.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

This model was created by applying LLM Compressor with calibration samples from UltraChat, as presented in the code snipet below.

Evaluation

This model was evaluated on the well-known OpenLLM v1, OpenLLM v2 and HumanEval_64 benchmarks using lm-evaluation-harness. The Reasoning evals were done using ligheval.

Accuracy

Category	Metric	Qwen/Qwen3-VL-235B-A22B-Instruct	RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4 (this model)	Recovery
OpenLLM	arc_challenge	72.95	71.59	98.13
	gsm8k	90.37	88.25	97.65
	hellaswag	87.94	86.80	98.70
	mmlu	87.12	86.22	98.97
	truthfulqa_mc2	63.31	62.37	98.52
	winogrande	81.93	80.43	98.17
	Average	80.60	79.28	98.35
Vision	mmmu_val	63.56	62.11	97.71
	chartqa	90.52	89.00	98.32
	Average	77.04	75.56	98.08

Reproduction

The results were obtained using the following commands:

Base model

Qwen/Qwen3-VL-235B-A22B-Instruct

(27)

17 items • Updated Apr 30 • 22

February 2026 Collection of third-party generative AI models validated by Red Hat AI for use across the Red Hat AI Product Portfolio. • 6 items • Updated Apr 30 • 2