CanItRun Logocanitrun.

Qwen3 235B-A22B (MoE)

Qwen3 235B-A22B (MoE) needs roughly 149.9 GB VRAM at Q4_K_M quantization (528.2 GB at FP16). 20 GPUs we track can run it fully in VRAM at 8k context.

20 GPUs run this natively · 2 with CPU offload

Alibaba235B params22B active (MoE)128k contextApache 2.0Commercial use ok

Qwen3 235B-A22B (MoE) is a Mixture of Experts (MoE) model with 235B total parameters but only 22B active per token developed by Alibaba. April 2025 flagship MoE with 235B total parameters but only 22B active. Reasoning-optimized architecture.

To run Qwen3 235B-A22B (MoE) locally: Q2_K needs ~100-120GB VRAM — multi-GPU server or Mac Studio M2/M3 Ultra required. As a MoE model, inference speed depends on active parameters (22B) rather than total size.

MoE efficiency with frontier-scale quality — designed for complex reasoning and agentic workflows.

VRAM at each quantization

Assumes 8k context. KV cache grows linearly with context length.

QuantWeightsKV cacheTotal
FP32940.0 GB1.58 GB1054.6 GB
BF16470.0 GB1.58 GB528.2 GB
FP16470.0 GB1.58 GB528.2 GB
Q8_0235.0 GB1.58 GB265.0 GB
Q6_K192.7 GB1.58 GB217.6 GB
Q5_K_M151.3 GB1.58 GB171.3 GB
Q4_K_M132.3 GB1.58 GB149.9 GB
Q3_K_M101.0 GB1.58 GB114.9 GB
Q2_Krec77.3 GB1.58 GB88.4 GB
NVFP4cuda117.5 GB1.58 GB133.4 GB

KV cache shown at 8k context (FP16). NVFP4 requires a CUDA GPU. Enable TurboQuant in the calculator to see reduced KV cache estimates.

Benchmarks

GPUs that run Qwen3 235B-A22B (MoE) natively (20)

Plus 2 GPUs that run it with CPU offload (slower)

Notes

Flagship reasoning MoE: 235B total, 22B active. Needs multi-GPU server.

Hugging Face ↗Ollama ↗Released 2025-04-29

Compare Qwen3 235B-A22B (MoE) with other models

Frequently asked questions

What are the VRAM requirements for Qwen3 235B-A22B (MoE)?
Qwen3 235B-A22B (MoE) requires approximately 149.9 GB of VRAM at Q4_K_M quantization, 265.0 GB at Q8, and 528.2 GB at FP16. These numbers assume 8k context window; VRAM scales linearly with context length due to the KV cache.
How many parameters does Qwen3 235B-A22B (MoE) have?
Qwen3 235B-A22B (MoE) has 235 billion total parameters, but only 22 billion are active per token thanks to its Mixture of Experts (MoE) architecture. This makes inference significantly faster than the total parameter count suggests.
How capable is Qwen3 235B-A22B (MoE)?
Qwen3 235B-A22B (MoE) achieves an MMLU-Pro score of 84.4, placing it among the most capable open-weight models available — competitive with frontier systems on general knowledge and reasoning.
Can Qwen3 235B-A22B (MoE) run on a 16 GB GPU?
No. At Q4_K_M, Qwen3 235B-A22B (MoE) needs 149.9 GB of VRAM — more than 16 GB. You will need a multi-GPU server.
Can Qwen3 235B-A22B (MoE) run on a 24 GB GPU?
No. Even at Q4_K_M, Qwen3 235B-A22B (MoE) needs 149.9 GB. Consider a multi-GPU server with 80 GB+ total VRAM.
What is the smallest quantization for Qwen3 235B-A22B (MoE) that fits in 24 GB of VRAM?
Qwen3 235B-A22B (MoE) cannot fit in 24 GB of VRAM at any standard quantization level. The minimum needed is 88.4 GB at Q2_K.
What GPU do I need to run Qwen3 235B-A22B (MoE) locally?
You need a multi-GPU server. At Q4_K_M, Qwen3 235B-A22B (MoE) needs 149.9 GB VRAM, more than any single consumer GPU. Consider 2–4× H100 or A100 GPUs.