Qwen3 VL 235B A22B Thinking — Hardware Requirements & GPU Compatibility
VisionFunctions
Qwen3-VL-235B-A22B-Thinking is the reasoning-enhanced edition of Alibaba's Qwen3-VL vision-language family, a mixture-of-experts model with roughly 22.8 billion active parameters out of about 235.7 billion total, that reasons step by step before answering on both text and visual inputs. Compared to the Instruct edition, Thinking emphasizes deeper multimodal reasoning for STEM, math, and causal analysis. The model can operate PC and mobile GUIs as a visual agent, generate code from images or video, judge spatial relationships and 3D layouts, and read OCR text in 32 languages. Given its scale, it needs a multi-GPU server to run even quantized. Context length is 262,144 tokens natively, expandable to 1,048,576 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in September 2025.
Qwen3 VL 235B A22B Thinking runs on a 192 GB+ Mac or a datacenter GPU
Best local pick → Mac Pro M2 Ultra (192 GB) · Q4_K_M · 143.3 GB · ~23 tok/s
Macs from 128 GB (Q4_0 · ~26 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen3 VL 235B A22B Thinking
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run qwen3-vl:235bQ4_K_M runs on one GH200 Grace Hopper Superchip 144 GB · 16K context
Download: Q4_K_M/Qwen3-VL-235B-A22B-Thinking-Q4_K_M-00001-of-00003.gguf142.15 GB + 2 partsunsloth
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 96 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on B200 (192 GB) (48 GB headroom) · Q4_K_M
- Generation speed
- ~128 tok/s
- generation speed
- Cost per 1M output tokens
- $12.97
- per 1M output tokens
How Much VRAM Does Qwen3 VL 235B A22B Thinking Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 100.7 GB | 103.6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Runs on Instinct MI250X 128 GB | |
| 103.6 GB | 106.6 GB | 3-bit small — 3-bit small quantization | Runs on Instinct MI250X 128 GB | |
| 115.4 GB | 118.4 GB | 3-bit medium — 3-bit medium quantization | Runs on Instinct MI250X 128 GB | |
| 118.3 GB | 121.3 GB | 4-bit · legacy — 4-bit legacy quantization | Runs on Instinct MI250X 128 GB | |
| 141.9 GB | 144.9 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Runs on GH200 Grace Hopper Superchip 144 GB | |
| 168.4 GB | 171.4 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Runs on B200 192 GB | |
| 194.9 GB | 197.9 GB | 6-bit, very good — 6-bit quantization, very good quality | Runs on Instinct MI325X 256 GB | |
| 236.2 GB | 239.1 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Runs on Instinct MI325X 256 GB |
Selected Q4_K_M
4-bit medium quantization143.3GBat 16K context
- Weights
- 141.4 GB
- KV cache
- 1.6 GB
- Overhead
- 0.3 GB
Server-class: ~143.3 GB at 16K context · one GH200 Grace Hopper Superchip 144 GB
Or .
Which Hardware Can Run Qwen3 VL 235B A22B Thinking?
Q4_K_M · 141.9 GBQwen3 VL 235B A22B Thinking (Q4_K_M) requires 141.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 185+ GB is recommended. Using the full 262K context window can add up to 25.0 GB, bringing total usage to 166.9 GB. No consumer GPU has enough memory. 4 devices with unified memory can run Qwen3 VL 235B A22B Thinking, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Pro M2 Ultra (192 GB).
128–144 GB
Q4_K_M · best fit Q4_0 (119.7 GB)
4 GPUs · 2 Mac classes · 1 device family
GH200 Grace Hopper Superchip~114Simulate output on GH200 Grace Hopper SuperchipH200 NVL~113Simulate output on H200 NVLH200 SXM~113Simulate output on H200 SXMM2 Ultra*128 GB~26Simulate output on Mac Pro M2 Ultra (128 GB)M5 Max128 GB~22Simulate output on Mac Studio M5 Max (128 GB)GB10~14Simulate output on NVIDIA DGX Spark192+ GB
fits · 48.7 GB free · up to 256K ctx
6 GPUs · 1 Mac class · 2 device families
B200~128Simulate output on B200B300~128Simulate output on B300Instinct MI350X~46Simulate output on Instinct MI350XM3 Ultra*256–512 GB~23Simulate output on Mac Studio (M3 Ultra, 256GB)8x H100 SXM5~168Simulate output on NVIDIA DGX H1008x A100 SXM4~155Simulate output on NVIDIA DGX A100 640GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Consumer GPUs (up to 32 GB) and Macs up to 96 GB: too small for this model (needs ≥ 93.2 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
How good is Qwen3 VL 235B A22B Thinking?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
This is the single board showing results for this model; badges show who ran the test.
- LMArena Text
LMArena · Oct 2026Arena
Arena1394.7
#54/188 open
Alternatives to Qwen3 VL 235B A22B Thinking
Qwen 3 family · 79 models →Similar models
5| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniMax M2.7MiniMax | 107.4 | 139.6 GB | —needs > 24 GB | same size |
| Command A Plus 05 2026 BF16Cohere | — | 132.1 GB | —needs > 24 GB | same size |
| DeepSeek V2.5 1210DeepSeek | — | 142.9 GB | —needs > 24 GB | same size |
| Laguna M.1poolside | — | 138.1 GB | —needs > 24 GB | same size |
| Llama 3 1 Nemotron Ultra 253B V1NVIDIA | — | 564.2 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- Alibaba
- Family
- Qwen 3
- Parameters
- 235.7B
- Active parameters
- 22.8B per token
- Architecture
- Qwen3VLMoeForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-09-22
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen3 VL 235B A22B Thinking need?
Qwen3 VL 235B A22B Thinking requires 141.9 GB of VRAM at Q4_K_M, or 471.8 GB at BF16. Full 262K context adds up to 25.0 GB (166.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 235.7B × 4.8 bits ÷ 8 = 141.4 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 25.5 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Qwen3 VL 235B A22B Thinking?
No — Qwen3 VL 235B A22B Thinking requires at least 91.8 GB at IQ3_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for Qwen3 VL 235B A22B Thinking?
For Qwen3 VL 235B A22B Thinking, Q4_K_M (141.9 GB) offers the best balance of quality and VRAM usage. Q5_K_S (162.5 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XXS at 91.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen3 VL 235B A22B Thinking on a Mac?
Yes — Mac Pro M2 Ultra (128 GB) and 14 other Macs can run Qwen3 VL 235B A22B Thinking, the smallest at Q4_0. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 141.9 GB of usable unified memory (RAM minus macOS overhead), from Mac Pro M2 Ultra (192 GB).
Can I run Qwen3 VL 235B A22B Thinking locally?
Yes — Qwen3 VL 235B A22B Thinking can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3 VL 235B A22B Thinking?
At Q4_K_M, Qwen3 VL 235B A22B Thinking can reach ~46 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 13.7 GB active ÷ (8000 × 0.65) = 2.64 ms, plus 94 layers × 0.055 ms = 5.17 ms, so 1000 ÷ 7.81 ms = ~128 tok/s
Estimated speed at Q4_K_M (141.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen3 VL 235B A22B Thinking?
At Q4_K_M, the download is about 141.40 GB. The full-precision BF16 version is 471.34 GB. The smallest option (IQ3_XXS) is 91.32 GB.
Which GPUs can run Qwen3 VL 235B A22B Thinking?
No single consumer GPU has enough VRAM to run Qwen3 VL 235B A22B Thinking at Q4_K_M (141.9 GB). Multi-GPU or professional hardware is required.
Which devices can run Qwen3 VL 235B A22B Thinking?
4 devices with unified memory can run Qwen3 VL 235B A22B Thinking at Q4_K_M (141.9 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.