Qwen · text

Qwen3-Omni-30B-A3B-Instruct

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

Qwen3-Omni-30B-A3B-Instruct at Q4_K_M is exactly 18,557,053,952 bytes (17.28 GiB / 18.56 GB) — an effective 4.210 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)From the file· KV per layer
Parameters
35.3B
Architecture
qwen3vlmoe
null layers
Context
—
native (config.json)
License
—

Shipped quantizations

● exact bytes, summed from published files
QuantSize●Exact bytes●Effective bpw●Tensors●Publisher
Q4_K_M17.28 GiB18,557,053,9524.210—ggml-org
Q4_K_M17.28 GiB18,557,054,1444.210—TrevorJS
Q8_030.25 GiB32,484,494,3367.370—ggml-org
Q8_030.25 GiB32,484,494,5287.370—TrevorJS
BF1656.90 GiB61,096,856,57613.862—ggml-org
F162 shards63.50 GiB68,183,680,67215.470—TrevorJS

Compare with

same modality, comparable size
vs Qwen3-Coder-30B-A3B-Instructvs Qwen3.6-27Bvs Qwen3.8-27Bvs gemma-4-E4B-itvs Qwen3-30B-A3B-Thinking-2507vs Qwen3-4BAll alternatives →Will it fit on my card? →

Will it run on your card?

full quant x context sweep
By VRAM:8GB12GB16GB24GB32GB48GB
Radeon RX 6500 XT 4GBGeForce RTX 3050 6GBGeForce RTX 5050 8GBGeForce RTX 3080 10GBGeForce RTX 2080 Ti 11GBGeForce RTX 5070 12GBGeForce RTX 5060 Ti 16GBApple M3 Pro 18GBGeForce RTX 3080 Ti 20GBGeForce RTX 5090 D V2 24GBGeForce RTX 5090 D 32GBApple M5 Max 36GBApple M5 Pro 48GBApple M5 Max 64GBApple M3 Ultra 96GBApple M5 Max 128GBApple M2 Ultra 192GBApple M3 Ultra 256GBApple M3 Ultra 512GB

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 18.47 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
no
Experts
—
Experts per token
—
use_sliding_window
—

Questions people ask

How much VRAM does Qwen3-Omni-30B-A3B-Instruct need?
Q4_K_M is exactly 18,557,053,952 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-Instruct 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.