Qwen 3 235B-A22B (MoE) — VRAM Requirements
Written by Jakub Rusinowski · Last updated April 28, 2025
How much GPU VRAM you need to run Qwen 3 Qwen 3 235B-A22B (MoE) by Alibaba Cloud locally, a 235B-parameter model. Figures are quantized weights + KV cache + framework overhead, computed from the model's parameter count and published architecture — not a throughput model. See /en/methodology.
Qwen 3 235B-A22B (MoE) needs about 144 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 77.3 GB | 79.6 GB |
| Q3_K_M | 3.41 | 100.2 GB | 102.5 GB |
| Q4_K_M | 4.83 | 141.9 GB | 144.3 GB |
| Q5_K_M | 5.67 | 166.6 GB | 168.9 GB |
| Q6_K | 6.56 | 192.7 GB | 195.1 GB |
| Q8_0 | 8.50 | 249.7 GB | 252.1 GB |
| F16 | 16.00 | 470.0 GB | 472.4 GB |
Switch quantization in the interactive calculator, or see the full Qwen 3 model page.
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Add this badge to your model card
Model creators: paste this into your Hugging Face model card README to link readers straight to this VRAM breakdown.
[](https://llmconfigurator.com/en/vram-calculator/qwen3-235b-a22b?utm_source=badge&utm_medium=referral&utm_campaign=readme_badge&utm_content=qwen3-235b-a22b)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.