Skip to content
localmodel.run

Model family · 3 sizes

Qwen3-VL: which size runs locally?

Qwen3-VL comes in 3 sizes, from 4.44B to 31.1B. Some sizes are Mixture-of-Experts, so they run faster than their memory footprint suggests. Here is each size with its Q4_K_M weight, the memory it needs, and the hardware that runs it.

Sizes
3
Smallest
4.44B
Largest
31.1B
Runs from
6GB

The Qwen3-VL lineup

Smallest first Q4_K_M · min memory

"Needs" is the sourced minimum memory for Q4_K_M with a small context. Larger context needs more.

Which Qwen3-VL fits your memory

6GB

Largest that fits: Qwen3-VL 4B (4.44B), best case on Nvidia GeForce RTX 2060 (6GB).

Tight
8GB

Largest that fits: Qwen3-VL 4B (4.44B), best case on Nvidia GeForce RTX 3060 Ti (8GB).

Yes
12GB

Largest that fits: Qwen3-VL 8B (8.77B), best case on Nvidia GeForce RTX 4070 (12GB).

Yes
16GB

Largest that fits: Qwen3-VL 8B (8.77B), best case on Nvidia GeForce RTX 4080 (16GB).

Yes
24GB

Largest that fits: Qwen3-VL 30B-A3B (31.1B), best case on Nvidia GeForce RTX 4090 (24GB).

Yes
32GB

Largest that fits: Qwen3-VL 30B-A3B (31.1B), best case on Nvidia GeForce RTX 5090 (32GB).

Yes
48GB

Largest that fits: Qwen3-VL 30B-A3B (31.1B), best case on Apple M5 Pro (48GB).

Yes
64GB

Largest that fits: Qwen3-VL 30B-A3B (31.1B), best case on Apple M4 Max (64GB).

Yes
128GB

Largest that fits: Qwen3-VL 30B-A3B (31.1B), best case on Apple M5 Max (128GB).

Yes
256GB

Largest that fits: Qwen3-VL 30B-A3B (31.1B), best case on Apple M3 Ultra (256GB).

Yes

Best case means the most capable device at that size (usually a discrete GPU). A Mac at the same size sits roughly one rung lower; see the per-size breakdown on each memory budget page.

FAQ

Which Qwen3-VL size should I run locally?

Pick the largest size your memory allows. On 6GB (best case) up to Qwen3-VL 4B; On 8GB (best case) up to Qwen3-VL 4B; On 12GB (best case) up to Qwen3-VL 8B; On 16GB (best case) up to Qwen3-VL 8B; On 24GB (best case) up to Qwen3-VL 30B-A3B; On 32GB (best case) up to Qwen3-VL 30B-A3B; On 48GB (best case) up to Qwen3-VL 30B-A3B; On 64GB (best case) up to Qwen3-VL 30B-A3B; On 128GB (best case) up to Qwen3-VL 30B-A3B; On 256GB (best case) up to Qwen3-VL 30B-A3B. Smaller sizes run faster and leave headroom for context.

What is the smallest Qwen3-VL model?

Qwen3-VL 4B at 4.44B parameters, about 3.11 GB on disk at Q4_K_M and roughly 4 GB of memory to run. It is the one to use on phones and 8 GB machines.

What is the largest Qwen3-VL model and what does it need?

Qwen3-VL 30B-A3B at 31.1B (mixture of experts), about 18.29 GB at Q4_K_M and roughly 21 GB of memory. It fits a high-memory desktop GPU or Mac.

Understand the numbers

Short guides to the ideas behind Qwen3-VL's memory and quant figures.

Sources

Memory figures are estimates at Q4_K_M. See methodology.