How much VRAM does Qwen3-Omni-30B-A3B-Thinking need?

Q4_K_M is exactly 18,557,053,248 bytes (17.28 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

Qwen · text

Qwen3-Omni-30B-A3B-Thinking

Qwen/Qwen3-Omni-30B-A3B-Thinking

Qwen3-Omni-30B-A3B-Thinking at Q4_K_M is exactly 18,557,053,248 bytes (17.28 GiB / 18.56 GB) — an effective 4.680 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)From the file· KV per layer

Parameters

31.7B

Architecture

qwen3vlmoe

null layers

Context

—

native (config.json)

License

—

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_K_M	17.28 GiB	18,557,053,248	4.680	—	ggml-org
Q8_0	30.25 GiB	32,484,493,632	8.193	—	ggml-org
BF16	56.90 GiB	61,096,855,872	15.409	—	ggml-org

Compare with

same modality, comparable size

vs Qwen3-Coder-30B-A3B-Instruct vs Qwen3.6-27B vs Qwen3.8-27B vs gemma-4-E4B-it vs Qwen3-30B-A3B-Thinking-2507 vs Qwen3-4B All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 16.62 GiB. The real file is 17.28 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from config.json

Layers

—

Attention heads

—

KV heads

—

Head dim

—

Hidden size

—

Vocab

—

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does Qwen3-Omni-30B-A3B-Thinking need?: Q4_K_M is exactly 18,557,053,248 bytes (17.28 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of Qwen3-Omni-30B-A3B-Thinking should I use?: Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.