Alibaba/Mixture of Experts

Qwen3-VL 235B A22B Instruct

Name: Qwen3-VL 235B A22B Instruct
Author: Alibaba

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.

chatvisionmultilingualreasoningagentic

235B

Parameters (22B active)

256K

Context length

Benchmarks

Quantizations

Architecture

MoE

Released

2025-10-15

Layers

KV Heads

Head Dim

128

Family

qwen

Quantization Options

Quant	Bits	VRAM	Quality
IQ2_XXS	2.38	70.4 GB	low
IQ2_M	2.93	86.6 GB	low
Q2_K	3.16	93.3 GB	low
IQ3_XXS	3.25	96.0 GB	low
IQ3_XS	3.5	103.3 GB	low
Q3_K_S	3.64	107.4 GB	low
IQ3_M	3.76	110.9 GB	low
Q3_K_M	4	118.0 GB	low
Q3_K_L	4.3	126.8 GB	moderate
IQ4_XS	4.46	131.5 GB	moderate
Q4_K_S	4.67	137.7 GB	moderate
Q4_K_M	4.89	144.1 GB	good
Q5_K_S	5.57	164.1 GB	good
Q5_K_M	5.7	167.9 GB	good
Q6_K	6.56	193.2 GB	excellent
Q8_0	8.5	250.2 GB	lossless
FP16	16	470.5 GB	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN QWEN3-VL 235B A22B INSTRUCT NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (14)

MMLU-PRO82.3

GPQA Diamond71.2

AIME70.7

AA Math70.7

MATH-50070.7

LiveCodeBench59.4

IFBench42.7

SciCode35.9

τ²-Bench35.1

AA Long Context31.7

AA Intelligence20.8

AA Coding16.5

Terminal-Bench6.8

HLE6.3

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run qwen:235b-q4_K_M

Tag may need adjustment — check ollama.com/library/qwen for available tags.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace GGUF Downloads Build Hardware